---
title: "A Survey of Self-Evolving Agents — paper by Gao et al. (2025)"
description: "This survey does not introduce new data or experiments. 382 references, cited by 33 papers here."
authors: ["Huan-ang Gao", "Jiayi Geng", "Wenyue Hua", "Mengkang Hu", "Xinzhe Juan", "Hongzhang Liu", "Shilong Liu", "Jiahao Qiu", "Xuan Qi", "Yiran Wu", "Hongru Wang", "Han Xiao", "Yuhang Zhou", "Shaokun Zhang", "Jiayi Zhang", "Jinyu Xiang", "Yixiong Fang", "Qiwen Zhao", "Dongrui Liu", "Qihan Ren", "Cheng Qian", "Zhenhailong Wang", "Minda Hu", "Huazheng Wang", "Qingyun Wu", "Heng Ji", "Mengdi Wang"]
year: 2025
venue: "arXiv:2507.21046"
source: "https://arxiv.org/abs/2507.21046"
doi: "10.48550/arxiv.2507.21046"
arxiv: "2507.21046"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/gao-2025-survey-self-evolving-agents-where/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/gao-2025-survey-self-evolving-agents-where/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/) / A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

# A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence

**Authors:** [Huan-ang Gao](https://md.research.elamur.ai/free/en/authors/huan-ang-gao/), [Jiayi Geng](https://md.research.elamur.ai/free/en/authors/jiayi-geng/), [Wenyue Hua](https://md.research.elamur.ai/free/en/authors/wenyue-hua/), [Mengkang Hu](https://md.research.elamur.ai/free/en/authors/mengkang-hu/), Xinzhe Juan, [Hongzhang Liu](https://md.research.elamur.ai/free/en/authors/hongzhang-liu/), [Shilong Liu](https://md.research.elamur.ai/free/en/authors/shilong-liu/), [Jiahao Qiu](https://md.research.elamur.ai/free/en/authors/jiahao-qiu/), [Xuan Qi](https://md.research.elamur.ai/free/en/authors/xuan-qi/), [Yiran Wu](https://md.research.elamur.ai/free/en/authors/yiran-wu/), [Hongru Wang](https://md.research.elamur.ai/free/en/authors/hongru-wang/), [Han Xiao](https://md.research.elamur.ai/free/en/authors/han-xiao/), [Yuhang Zhou](https://md.research.elamur.ai/free/en/authors/yuhang-zhou/), [Shaokun Zhang](https://md.research.elamur.ai/free/en/authors/shaokun-zhang/), [Jiayi Zhang](https://md.research.elamur.ai/free/en/authors/jiayi-zhang/), Jinyu Xiang, Yixiong Fang, Qiwen Zhao, [Dongrui Liu](https://md.research.elamur.ai/free/en/authors/dongrui-liu/), Qihan Ren, [Cheng Qian](https://md.research.elamur.ai/free/en/authors/cheng-qian/), [Zhenhailong Wang](https://md.research.elamur.ai/free/en/authors/zhenhailong-wang/), Minda Hu, [Huazheng Wang](https://md.research.elamur.ai/free/en/authors/huazheng-wang/), [Qingyun Wu](https://md.research.elamur.ai/free/en/authors/qingyun-wu/), [Heng Ji](https://md.research.elamur.ai/free/en/authors/heng-ji/) and [Mengdi Wang](https://md.research.elamur.ai/free/en/authors/mengdi-wang/) · **Year:** 2025 · **Venue:** arXiv:2507.21046 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2507.21046) · [PDF](https://arxiv.org/pdf/2507.21046) · [DOI 10.48550/arxiv.2507.21046](https://doi.org/10.48550/arxiv.2507.21046) · [arXiv 2507.21046](https://arxiv.org/abs/2507.21046) · [OpenAlex](https://openalex.org/W7077063733)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [33](https://md.research.elamur.ai/free/en/papers/gao-2025-survey-self-evolving-agents-where/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Today's LLMs are essentially frozen once trained. They cannot update their own parameters or behavior when they meet unfamiliar tasks, shifting knowledge, or changing interaction settings, and this becomes a serious limitation when agents work in open, interactive environments. This survey does not introduce new data or experiments. Instead, it consolidates a fast-growing body of work on agents that improve themselves from experience. The authors argue that self-evolution is defined by where autonomy sits, not by the training algorithm. A self-evolving agent decides on its own what to learn and when, while traditional pipelines rely on human-curated updates. The literature is organized along three axes:
- **What** changes: model, memory, prompts, tools, architecture.
- **When** change happens: within a task versus between tasks.
- **How** it is driven: scalar rewards, textual feedback, single-agent versus multi-agent setups.

The survey also reviews evaluation practice, applications, and open problems. Its main value is a shared vocabulary and design map for a field whose boundaries are still unsettled. That makes it a useful entry point for anyone building adaptive LLM agents.

## Key points
- Sections 3–5 map onto the three axes. Evolving components include policy, lessons, memory, prompts, and tool creation, mastery, and selection. Adaptation timing is split into intra-test-time and inter-test-time stages.
- Example systems catalogued include:
  - Reflexion, Self-Refine, and SCoRe
  - Mem0 and Agent Workflow Memory
  - PromptBreeder, DSPy, and TextGrad
  - Voyager and Alita
  - Toolformer and Gorilla
  - Darwin Godel Machine
- Application areas covered include coding and software engineering, education, healthcare, and virtual assistants.
- A practical safety checklist is included, covering reward-hacking detection, automated red-teaming, PII sanitization, protection against memory poisoning, and human approval for high-stakes actions.
- Open problems include catastrophic forgetting, preserving alignment during autonomous updates, agent–environment co-evolution, and the static nature of current multi-agent benchmarks. The paper is arXiv:2507.21046, reviewed on OpenReview, with a curated list at github.com/CharlesQ9/Self-Evolving-Agents.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works

## Cite

Cite as: Huan-ang Gao, Jiayi Geng, Wenyue Hua, Mengkang Hu, Xinzhe Juan, Hongzhang Liu, Shilong Liu, Jiahao Qiu, Xuan Qi, Yiran Wu, Hongru Wang, Han Xiao, Yuhang Zhou, Shaokun Zhang, Jiayi Zhang, Jinyu Xiang, Yixiong Fang, Qiwen Zhao, Dongrui Liu, Qihan Ren, Cheng Qian, Zhenhailong Wang, Minda Hu, Huazheng Wang, Qingyun Wu, Heng Ji and Mengdi Wang. 2025. A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence. arXiv:2507.21046.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{gao2025survey,
  title = {{A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence}},
  author = {Huan-ang Gao, Jiayi Geng, Wenyue Hua, Mengkang Hu, Xinzhe Juan, Hongzhang Liu, Shilong Liu, Jiahao Qiu, Xuan Qi, Yiran Wu, Hongru Wang, Han Xiao, Yuhang Zhou, Shaokun Zhang, Jiayi Zhang, Jinyu Xiang, Yixiong Fang, Qiwen Zhao, Dongrui Liu, Qihan Ren, Cheng Qian, Zhenhailong Wang, Minda Hu, Huazheng Wang, Qingyun Wu, Heng Ji and Mengdi Wang},
  year = {2025},
  doi = {10.48550/arxiv.2507.21046},
  eprint = {2507.21046},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2507.21046}
}
```

- [← previous A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility](https://md.research.elamur.ai/free/en/papers/hochlehnert-2025-sober-look-progress-language-model/)
- [next → AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator](https://md.research.elamur.ai/free/en/papers/fan-2025-ai-hospital-benchmarking-large-language/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/4/)

## References

382 references, 105 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Emre Can Acikgoz, Cheng Qian, Heng Ji, Dilek Hakkani-Tür, and Gokhan Tur. Self-improving llm agents at test-time. arXiv preprint arXiv:2510.07841, 2025. — [arXiv:2510.07841](https://arxiv.org/abs/2510.07841) [find](https://scholar.google.com/scholar?q=Emre+Can+Acikgoz%2C+Cheng+Qian%2C+Heng+Ji%2C+Dilek+Hakkani%2DT%C3%BCr%2C+and+Gokhan+Tur%2E+Self%2Dimproving+llm+agents+at+test%2Dtime%2E+arXiv+preprint+arXiv%3A2510%2E07841%2C+2025%2E+%E2%80%94+%5BarXiv%3A2510%2E07841%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2510)
2. Saaket Agashe, Kyle Wong, Vincent Tu, Jiachen Yang, Ang Li, and Xin Eric Wang. Agent S2: A compositional generalist-specialist framework for computer use agents. arXiv preprint arXiv:2504.00906, 2025. — [arXiv:2504.00906](https://arxiv.org/abs/2504.00906) [find](https://scholar.google.com/scholar?q=Saaket+Agashe%2C+Kyle+Wong%2C+Vincent+Tu%2C+Jiachen+Yang%2C+Ang+Li%2C+and+Xin+Eric+Wang%2E+Agent+S2%3A+A+compositional+generalist%2Dspecialist+framework+for+computer+use+agents%2E+arXiv+preprint+arXiv%3A2504%2E00906%2C+2025%2E)
3. Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, and David Ha. Evolutionary optimization of model merging recipes. Nature Machine Intelligence, 7(2):195–204, 2025. [find](https://scholar.google.com/scholar?q=Takuya+Akiba%2C+Makoto+Shing%2C+Yujin+Tang%2C+Qi+Sun%2C+and+David+Ha%2E+Evolutionary+optimization+of+model+merging+recipes%2E+Nature+Machine+Intelligence%2C+7%282%29%3A195%E2%80%93204%2C+2025%2E)
4. Reem Aleithan, Haoran Xue, Mohammad Mahdi Mohajer, Elijah Nnorom, Gias Uddin, and Song Wang. [Swe-bench+: Enhanced coding benchmark for llms](https://md.research.elamur.ai/free/en/papers/aleithan-2024-swe-bench-enhanced-coding/). arXiv preprint arXiv:2410.06992, 2024.
5. Mohammad Almansoori, Komal Kumar, and Hisham Cholakkal. Self-evolving multi-agent simulations for realistic clinical interactions. arXiv preprint arXiv:2503.22678, 2025a. — [arXiv:2503.22678](https://arxiv.org/abs/2503.22678) [find](https://scholar.google.com/scholar?q=Mohammad+Almansoori%2C+Komal+Kumar%2C+and+Hisham+Cholakkal%2E+Self%2Devolving+multi%2Dagent+simulations+for+realistic+clinical+interactions%2E+arXiv+preprint+arXiv%3A2503%2E22678%2C+2025a%2E+%E2%80%94+%5BarXiv%3A2503%2E22678%5D%28https%3A%2F%2F)
6. Mohammad Almansoori, Komal Kumar, and Hisham Cholakkal. Self-evolving multi-agent simulations for realistic clinical interactions. arXiv preprint arXiv:2503.22678, 2025b. — [arXiv:2503.22678](https://arxiv.org/abs/2503.22678) [find](https://scholar.google.com/scholar?q=Mohammad+Almansoori%2C+Komal+Kumar%2C+and+Hisham+Cholakkal%2E+Self%2Devolving+multi%2Dagent+simulations+for+realistic+clinical+interactions%2E+arXiv+preprint+arXiv%3A2503%2E22678%2C+2025b%2E+%E2%80%94+%5BarXiv%3A2503%2E22678%5D%28https%3A%2F%2F)
7. Shun-ichi Amari. Backpropagation and stochastic gradient descent method. Neurocomputing, 5(4-5):185–196, 1993. [find](https://scholar.google.com/scholar?q=Shun%2Dichi+Amari%2E+Backpropagation+and+stochastic+gradient+descent+method%2E+Neurocomputing%2C+5%284%2D5%29%3A185%E2%80%93196%2C+1993%2E)
8. Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian, Derek Duenas, Maxwell Lin, Justin Wang, Dan Hendrycks, Andy Zou, Zico Kolter, Matt Fredrikson, et al. Agentharm: A benchmark for measuring harmfulness of llm agents. arXiv preprint arXiv:2410.09024, 2024. — [arXiv:2410.09024](https://arxiv.org/abs/2410.09024) [find](https://scholar.google.com/scholar?q=Maksym+Andriushchenko%2C+Alexandra+Souly%2C+Mateusz+Dziemian%2C+Derek+Duenas%2C+Maxwell+Lin%2C+Justin+Wang%2C+Dan+Hendrycks%2C+Andy+Zou%2C+Zico+Kolter%2C+Matt+Fredrikson%2C+et+al%2E+Agentharm%3A+A+benchmark+for+measuring+har)
9. Usman Anwar, Abulhair Saparov, Javier Rando, Daniel Paleka, Miles Turpin, Peter Hase, Ekdeep Singh Lubana, Erik Jenner, Stephen Casper, Oliver Sourbut, et al. [Foundational challenges in assuring alignment and safety of large language models](https://md.research.elamur.ai/free/en/papers/anwar-2024-foundational-challenges-assuring-alignment-safety/). arXiv preprint arXiv:2404.09932, 2024.
10. Leonhard Applis, Yuntong Zhang, Shanchao Liang, Nan Jiang, Lin Tan, and Abhik Roychoudhury. Unified software engineering agent as ai software engineer. arXiv preprint arXiv:2506.14683, 2025. — [arXiv:2506.14683](https://arxiv.org/abs/2506.14683) [find](https://scholar.google.com/scholar?q=Leonhard+Applis%2C+Yuntong+Zhang%2C+Shanchao+Liang%2C+Nan+Jiang%2C+Lin+Tan%2C+and+Abhik+Roychoudhury%2E+Unified+software+engineering+agent+as+ai+software+engineer%2E+arXiv+preprint+arXiv%3A2506%2E14683%2C+2025%2E+%E2%80%94+%5BarXiv%3A)
11. Henrique Assumpção, Diego Ferreira, Leandro Campos, and Fabricio Murai. Codeevolve: An open source evolutionary coding agent for algorithm discovery and optimization. arXiv preprint arXiv:2510.14150, 2025. — [arXiv:2510.14150](https://arxiv.org/abs/2510.14150) [find](https://scholar.google.com/scholar?q=Henrique+Assump%C3%A7%C3%A3o%2C+Diego+Ferreira%2C+Leandro+Campos%2C+and+Fabricio+Murai%2E+Codeevolve%3A+An+open+source+evolutionary+coding+agent+for+algorithm+discovery+and+optimization%2E+arXiv+preprint+arXiv%3A2510%2E14150%2C+)
12. Ruhana Azam, Aditya Vempaty, and Ashish Jagmohan. Reflection-augmented planning (ReAP): Memory for web navigation agents. arXiv preprint arXiv:2506.02158, 2025. — [arXiv:2506.02158](https://arxiv.org/abs/2506.02158) [find](https://scholar.google.com/scholar?q=Ruhana+Azam%2C+Aditya+Vempaty%2C+and+Ashish+Jagmohan%2E+Reflection%2Daugmented+planning+%28ReAP%29%3A+Memory+for+web+navigation+agents%2E+arXiv+preprint+arXiv%3A2506%2E02158%2C+2025%2E+%E2%80%94+%5BarXiv%3A2506%2E02158%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
13. Yaniv Azaria and Moshe Sipper. Gp-gammon: Using genetic programming to evolve backgammon players. In Maarten Keijzer, Andrea Tettamanzi, Pierre Collet, Jano van Hemert, and Marco Tomassini (eds.), Genetic Programming, pp. 132–142, Berlin, Heidelberg, 2005. Springer Berlin Heidelberg. ISBN 978-3-540-… [find](https://scholar.google.com/scholar?q=Yaniv+Azaria+and+Moshe+Sipper%2E+Gp%2Dgammon%3A+Using+genetic+programming+to+evolve+backgammon+players%2E+In+Maarten+Keijzer%2C+Andrea+Tettamanzi%2C+Pierre+Collet%2C+Jano+van+Hemert%2C+and+Marco+Tomassini+%28eds%2E%29%2C+Gen)
14. Eugene Bagdasarian, Ren Yi, Sahra Ghalebikesabi, Peter Kairouz, Marco Gruteser, Sewoong Oh, Borja Balle, and Daniel Ramage. Airgapagent: Protecting privacy-conscious conversational agents. In Proceedings of the 2024 on ACM SIGSAC Conference on Computer and Communications Security, pp. 3868–3882, 202… [find](https://scholar.google.com/scholar?q=Eugene+Bagdasarian%2C+Ren+Yi%2C+Sahra+Ghalebikesabi%2C+Peter+Kairouz%2C+Marco+Gruteser%2C+Sewoong+Oh%2C+Borja+Balle%2C+and+Daniel+Ramage%2E+Airgapagent%3A+Protecting+privacy%2Dconscious+conversational+agents%2E+In+Proceedi)
15. Hao Bai, Yifei Zhou, Jiayi Pan, Mert Cemri, Alane Suhr, Sergey Levine, and Aviral Kumar. Digirl: Training in-the-wild device-control agents with autonomous reinforcement learning. Advances in Neural Information Processing Systems, 37:12461–12495, 2024. [find](https://scholar.google.com/scholar?q=Hao+Bai%2C+Yifei+Zhou%2C+Jiayi+Pan%2C+Mert+Cemri%2C+Alane+Suhr%2C+Sergey+Levine%2C+and+Aviral+Kumar%2E+Digirl%3A+Training+in%2Dthe%2Dwild+device%2Dcontrol+agents+with+autonomous+reinforcement+learning%2E+Advances+in+Neural+I)
16. Debabrota Basu and Udvas Das. The fair game: Auditing & debiasing ai algorithms over time. In Cambridge Forum on AI: Law and Governance, volume 1, pp. e27. Cambridge University Press, 2025. [find](https://scholar.google.com/scholar?q=Debabrota+Basu+and+Udvas+Das%2E+The+fair+game%3A+Auditing+%26+debiasing+ai+algorithms+over+time%2E+In+Cambridge+Forum+on+AI%3A+Law+and+Governance%2C+volume+1%2C+pp%2E+e27%2E+Cambridge+University+Press%2C+2025%2E)
17. James Bell, Luca Quarantiello, Ethan N Coleman, Ling Li, Meng Li, et al. The future of continual learning in the era of foundation models: Three key directions. arXiv preprint arXiv:2506.03320, 2025. — [arXiv:2506.03320](https://arxiv.org/abs/2506.03320) [find](https://scholar.google.com/scholar?q=James+Bell%2C+Luca+Quarantiello%2C+Ethan+N+Coleman%2C+Ling+Li%2C+Meng+Li%2C+et+al%2E+The+future+of+continual+learning+in+the+era+of+foundation+models%3A+Three+key+directions%2E+arXiv+preprint+arXiv%3A2506%2E03320%2C+2025%2E+)
18. Nikolas Belle, Dakota Barnes, Alfonso Amayuelas, Ivan Bercovich, Xin Eric Wang, and William Wang. Agents of change: Self-evolving llm agents for strategic planning. arXiv preprint arXiv:2506.04651, 2025. — [arXiv:2506.04651](https://arxiv.org/abs/2506.04651) [find](https://scholar.google.com/scholar?q=Nikolas+Belle%2C+Dakota+Barnes%2C+Alfonso+Amayuelas%2C+Ivan+Bercovich%2C+Xin+Eric+Wang%2C+and+William+Wang%2E+Agents+of+change%3A+Self%2Devolving+llm+agents+for+strategic+planning%2E+arXiv+preprint+arXiv%3A2506%2E04651%2C+20)
19. Yoshua Bengio, Jérôme Louradour, Ronan Collobert, and Jason Weston. [Curriculum learning](https://md.research.elamur.ai/free/en/papers/bengio-2009-curriculum-learning/). In Proceedings of the 26th annual international conference on machine learning, pp. 41–48, 2009.
20. Zhenni Bi, Kai Han, Chuanjian Liu, Yehui Tang, and Yunhe Wang. [Forest-of-thought: Scaling test-time compute for enhancing llm reasoning](https://md.research.elamur.ai/free/en/papers/bi-2024-forest-thought-scaling-test-time/). arXiv preprint arXiv:2412.09078, 2024.
21. Areeb Bilal, Muhammad Abdul Mohsin, Muhammad Umer, Muhammad Arslan Khan Bangash, et al. Meta-thinking in llms via multi-agent reinforcement learning: A survey. arXiv preprint arXiv:2504.14520, 2025. — [arXiv:2504.14520](https://arxiv.org/abs/2504.14520) [find](https://scholar.google.com/scholar?q=Areeb+Bilal%2C+Muhammad+Abdul+Mohsin%2C+Muhammad+Umer%2C+Muhammad+Arslan+Khan+Bangash%2C+et+al%2E+Meta%2Dthinking+in+llms+via+multi%2Dagent+reinforcement+learning%3A+A+survey%2E+arXiv+preprint+arXiv%3A2504%2E14520%2C+2025%2E+%E2%80%94)
22. Rogerio Bonatti, Dan Zhao, Francesco Bonacci, Dillon Dupont, Sara Abdali, Yinheng Li, Yadong Lu, Justin Wagle, Kazuhito Koishida, et al. Windows Agent Arena: Evaluating multi-modal OS agents at scale. arXiv preprint arXiv:2409.08264, 2024. — [arXiv:2409.08264](https://arxiv.org/abs/2409.08264) [find](https://scholar.google.com/scholar?q=Rogerio+Bonatti%2C+Dan+Zhao%2C+Francesco+Bonacci%2C+Dillon+Dupont%2C+Sara+Abdali%2C+Yinheng+Li%2C+Yadong+Lu%2C+Justin+Wagle%2C+Kazuhito+Koishida%2C+et+al%2E+Windows+Agent+Arena%3A+Evaluating+multi%2Dmodal+OS+agents+at+scale%2E)
23. Léon Bottou. Large-scale machine learning with stochastic gradient descent. In Proceedings of COMP-STAT’2010: 19th International Conference on Computational StatisticsParis France, August 22-27, 2010 Keynote, Invited and Contributed Papers, pp. 177–186. [find](https://scholar.google.com/scholar?q=L%C3%A9on+Bottou%2E+Large%2Dscale+machine+learning+with+stochastic+gradient+descent%2E+In+Proceedings+of+COMP%2DSTAT%E2%80%992010%3A+19th+International+Conference+on+Computational+StatisticsParis+France%2C+August+22%2D27%2C+2010+)
24. Stefan Braun, Daniel Neil, and Shih-Chii Liu. A curriculum learning method for improved noise robustness in automatic speech recognition. In 2017 25th European Signal Processing Conference (EUSIPCO), pp. 548–552. [find](https://scholar.google.com/scholar?q=Stefan+Braun%2C+Daniel+Neil%2C+and+Shih%2DChii+Liu%2E+A+curriculum+learning+method+for+improved+noise+robustness+in+automatic+speech+recognition%2E+In+2017+25th+European+Signal+Processing+Conference+%28EUSIPCO%29%2C+)
25. Yuxuan Cai, Yipeng Hao, Jie Zhou, Hang Yan, Zhikai Lei, Rui Zhen, Zhenhua Han, Yutao Yang, Junsong Li, Qianjun Pan, et al. Building self-evolving agents via experience-driven lifelong learning: A framework and benchmark. arXiv preprint arXiv:2508.19005, 2025. — [arXiv:2508.19005](https://arxiv.org/abs/2508.19005) [find](https://scholar.google.com/scholar?q=Yuxuan+Cai%2C+Yipeng+Hao%2C+Jie+Zhou%2C+Hang+Yan%2C+Zhikai+Lei%2C+Rui+Zhen%2C+Zhenhua+Han%2C+Yutao+Yang%2C+Junsong+Li%2C+Qianjun+Pan%2C+et+al%2E+Building+self%2Devolving+agents+via+experience%2Ddriven+lifelong+learning%3A+A+fram)
26. David Castillo-Bolado, Joseph Davidson, Finlay Gray, and Marek Rosa. Beyond prompts: Dynamic conversational benchmarking of large language models. In The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track, 2024. URL [https://openreview.net/forum?id=](https://openreview.net/forum?id=) twFlD3C… [↗](https://openreview.net/forum?id=)
27. Jun Shern Chan, Neil Chowdhury, Oliver Jaffe, James Aung, Dane Sherburn, Evan Mays, Giulio Starace, Kevin Liu, Leon Maksin, Tejal Patwardhan, et al. [Mle-bench: Evaluating machine learning agents on machine learning engineering](https://md.research.elamur.ai/free/en/papers/chan-2024-mle-bench-evaluating-machine/). arXiv preprint arXiv:2410.07095, 2024.
28. Chen Chen, Xinlong Hao, Weiwen Liu, Xu Huang, Xingshan Zeng, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, Yuefeng Huang, et al. Acebench: Who wins the match point in tool usage? arXiv preprint arXiv:2501.12851, 2025a. — [arXiv:2501.12851](https://arxiv.org/abs/2501.12851) [find](https://scholar.google.com/scholar?q=Chen+Chen%2C+Xinlong+Hao%2C+Weiwen+Liu%2C+Xu+Huang%2C+Xingshan+Zeng%2C+Shuai+Yu%2C+Dexun+Li%2C+Shuai+Wang%2C+Weinan+Gan%2C+Yuefeng+Huang%2C+et+al%2E+Acebench%3A+Who+wins+the+match+point+in+tool+usage%3F+arXiv+preprint+arXiv%3A25)
29. Guoxin Chen, Minpeng Liao, Chengxi Li, and Kai Fan. [Alphamath almost zero: process supervision without process](https://md.research.elamur.ai/free/en/papers/chen-2024-alphamath-almost-zero-process-supervision/). arXiv preprint arXiv:2405.03553, 2024a.
30. Hardy Chen, Haoqin Tu, Fali Wang, Hui Liu, Xianfeng Tang, Xinya Du, Yuyin Zhou, and Cihang Xie. [Sft or rl? an early investigation into training r1-like reasoning large vision-language models](https://md.research.elamur.ai/free/en/papers/chen-2025-sft-rl-early-investigation-training/). arXiv preprint arXiv:2504.11468, 2025b.
31. Howard Chen, Jiayi Geng, Adithya Bhaskar, Dan Friedman, and Danqi Chen. Continual memorization of factoids in language models. arXiv preprint arXiv:2411.07175, 2024b. [find](https://scholar.google.com/scholar?q=Howard+Chen%2C+Jiayi+Geng%2C+Adithya+Bhaskar%2C+Dan+Friedman%2C+and+Danqi+Chen%2E+Continual+memorization+of+factoids+in+language+models%2E+arXiv+preprint+arXiv%3A2411%2E07175%2C+2024b%2E)
32. Jiaqi Chen, Bang Zhang, Ruotian Ma, Peisong Wang, Xiaodan Liang, Zhaopeng Tu, Xiaolong Li, and Kwan-Yee K Wong. Spc: Evolving self-play critic via adversarial games for llm reasoning. arXiv preprint arXiv:2504.19162, 2025c. — [arXiv:2504.19162](https://arxiv.org/abs/2504.19162) [find](https://scholar.google.com/scholar?q=Jiaqi+Chen%2C+Bang+Zhang%2C+Ruotian+Ma%2C+Peisong+Wang%2C+Xiaodan+Liang%2C+Zhaopeng+Tu%2C+Xiaolong+Li%2C+and+Kwan%2DYee+K+Wong%2E+Spc%3A+Evolving+self%2Dplay+critic+via+adversarial+games+for+llm+reasoning%2E+arXiv+preprint+a)
33. Kai Chen, Xinfeng Li, Tianpei Yang, Hewei Wang, Wei Dong, and Yang Gao. Mdteamgpt: A self-evolving llm-based multi-agent framework for multi-disciplinary team medical consultation. arXiv preprint arXiv:2503.13856, 2025d. — [arXiv:2503.13856](https://arxiv.org/abs/2503.13856) [find](https://scholar.google.com/scholar?q=Kai+Chen%2C+Xinfeng+Li%2C+Tianpei+Yang%2C+Hewei+Wang%2C+Wei+Dong%2C+and+Yang+Gao%2E+Mdteamgpt%3A+A+self%2Devolving+llm%2Dbased+multi%2Dagent+framework+for+multi%2Ddisciplinary+team+medical+consultation%2E+arXiv+preprint+arXi)
34. Kai Chen, Ji Qi, Jing Huo, Pinzhuo Tian, Fanyu Meng, Xi Yang, and Yang Gao. A self-evolving framework for multi-agent medical consultation based on large language models. In ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1–5. [find](https://scholar.google.com/scholar?q=Kai+Chen%2C+Ji+Qi%2C+Jing+Huo%2C+Pinzhuo+Tian%2C+Fanyu+Meng%2C+Xi+Yang%2C+and+Yang+Gao%2E+A+self%2Devolving+framework+for+multi%2Dagent+medical+consultation+based+on+large+language+models%2E+In+ICASSP+2025%2D2025+IEEE+Inte)
35. Kaiyuan Chen, Yixin Ren, Yang Liu, Xiaobo Hu, Haotong Tian, Tianbao Xie, Fangfu Liu, Haoye Zhang, Hongzhang Liu, Yuan Gong, et al. xbench: Tracking agents productivity scaling with profession-aligned real-world evaluations. arXiv preprint arXiv:2506.13651, 2025f. — [arXiv:2506.13651](https://arxiv.org/abs/2506.13651) [find](https://scholar.google.com/scholar?q=Kaiyuan+Chen%2C+Yixin+Ren%2C+Yang+Liu%2C+Xiaobo+Hu%2C+Haotong+Tian%2C+Tianbao+Xie%2C+Fangfu+Liu%2C+Haoye+Zhang%2C+Hongzhang+Liu%2C+Yuan+Gong%2C+et+al%2E+xbench%3A+Tracking+agents+productivity+scaling+with+profession%2Daligned+)
36. Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Mathias Humbert, and Yang Zhang. When machine unlearning jeopardizes privacy. In Proceedings of the 2021 ACM SIGSAC conference on computer and communications security, pp. 896–911, 2021. [find](https://scholar.google.com/scholar?q=Min+Chen%2C+Zhikun+Zhang%2C+Tianhao+Wang%2C+Michael+Backes%2C+Mathias+Humbert%2C+and+Yang+Zhang%2E+When+machine+unlearning+jeopardizes+privacy%2E+In+Proceedings+of+the+2021+ACM+SIGSAC+conference+on+computer+and+com)
37. Qizhou Chen, Taolin Zhang, Xiaofeng He, Dongyang Li, Chengyu Wang, Longtao Huang, and Hui Xue. Lifelong knowledge editing for llms with retrieval-augmented continuous prompt learning. arXiv preprint arXiv:2405.03279, 2024c. [find](https://scholar.google.com/scholar?q=Qizhou+Chen%2C+Taolin+Zhang%2C+Xiaofeng+He%2C+Dongyang+Li%2C+Chengyu+Wang%2C+Longtao+Huang%2C+and+Hui+Xue%2E+Lifelong+knowledge+editing+for+llms+with+retrieval%2Daugmented+continuous+prompt+learning%2E+arXiv+preprint+a)
38. Simin Chen, Yiming Chen, Zexin Li, Yifan Jiang, Zhongwei Wan, Yixin He, Dezhi Ran, Tianle Gu, Haizhou Li, Tao Xie, et al. Recent advances in large langauge model benchmarks against data contamination: From static to dynamic evaluation. arXiv preprint arXiv:2502.17521, 2025g. — [arXiv:2502.17521](https://arxiv.org/abs/2502.17521) [find](https://scholar.google.com/scholar?q=Simin+Chen%2C+Yiming+Chen%2C+Zexin+Li%2C+Yifan+Jiang%2C+Zhongwei+Wan%2C+Yixin+He%2C+Dezhi+Ran%2C+Tianle+Gu%2C+Haizhou+Li%2C+Tao+Xie%2C+et+al%2E+Recent+advances+in+large+langauge+model+benchmarks+against+data+contamination%3A)
39. Weize Chen, Jiarui Yuan, Chen Qian, Cheng Yang, Zhiyuan Liu, and Maosong Sun. Optima: Optimizing effectiveness and efficiency for llm-based multi-agent system. arXiv preprint arXiv:2410.08115, 2024d. [find](https://scholar.google.com/scholar?q=Weize+Chen%2C+Jiarui+Yuan%2C+Chen+Qian%2C+Cheng+Yang%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+Optima%3A+Optimizing+effectiveness+and+efficiency+for+llm%2Dbased+multi%2Dagent+system%2E+arXiv+preprint+arXiv%3A2410%2E08115%2C+2024d%2E)
40. Zehui Chen, Weihua Du, Wenwei Zhang, Kuikun Liu, Jiangning Liu, Miao Zheng, Jingming Zhuo, Songyang Zhang, Dahua Lin, Kai Chen, et al. T-eval: Evaluating the tool utilization capability of large language models step by step. arXiv preprint arXiv:2312.14033, 2023. [find](https://scholar.google.com/scholar?q=Zehui+Chen%2C+Weihua+Du%2C+Wenwei+Zhang%2C+Kuikun+Liu%2C+Jiangning+Liu%2C+Miao+Zheng%2C+Jingming+Zhuo%2C+Songyang+Zhang%2C+Dahua+Lin%2C+Kai+Chen%2C+et+al%2E+T%2Deval%3A+Evaluating+the+tool+utilization+capability+of+large+langu)
41. Ziru Chen, Shijie Chen, Yuting Ning, Qianheng Zhang, Boshi Wang, Botao Yu, Yifei Li, Zeyi Liao, Chen Wei, Zitong Lu, et al. [Scienceagentbench: Toward rigorous assessment of language agents for data-driven scientific discovery](https://md.research.elamur.ai/free/en/papers/chen-2024-scienceagentbench-rigorous-assessment-language/). arXiv preprint arXiv:2410.05080, 2024e.
42. Zixiang Chen, Yihe Deng, Huizhuo Yuan, Kaixuan Ji, and Quanquan Gu. Self-play fine-tuning converts weak language models to strong language models. arXiv preprint arXiv:2401.01335, 2024f. [find](https://scholar.google.com/scholar?q=Zixiang+Chen%2C+Yihe+Deng%2C+Huizhuo+Yuan%2C+Kaixuan+Ji%2C+and+Quanquan+Gu%2E+Self%2Dplay+fine%2Dtuning+converts+weak+language+models+to+strong+language+models%2E+arXiv+preprint+arXiv%3A2401%2E01335%2C+2024f%2E)
43. Yi Cheng, Wenge Liu, Kaishuai Xu, Wenjun Hou, Yi Ouyang, Chak Tou Leong, Xian Wu, and Yefeng Zheng. Autopal: Autonomous adaptation to users for personal ai companionship. arXiv preprint arXiv:2406.13960, 2024. — [arXiv:2406.13960](https://arxiv.org/abs/2406.13960) [find](https://scholar.google.com/scholar?q=Yi+Cheng%2C+Wenge+Liu%2C+Kaishuai+Xu%2C+Wenjun+Hou%2C+Yi+Ouyang%2C+Chak+Tou+Leong%2C+Xian+Wu%2C+and+Yefeng+Zheng%2E+Autopal%3A+Autonomous+adaptation+to+users+for+personal+ai+companionship%2E+arXiv+preprint+arXiv%3A2406%2E139)
44. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. [Mem0: Building production-ready ai agents with scalable long-term memory](https://md.research.elamur.ai/free/en/papers/chhikara-2025-mem0-building-production-ready-ai/). arXiv preprint arXiv:2504.19413, 2025.
45. François Chollet. On the measure of intelligence. arXiv preprint arXiv:1911.01547, 2019. [find](https://scholar.google.com/scholar?q=Fran%C3%A7ois+Chollet%2E+On+the+measure+of+intelligence%2E+arXiv+preprint+arXiv%3A1911%2E01547%2C+2019%2E)
46. Sanjiban Choudhury. Process reward models for llm agents: Practical framework and directions. arXiv preprint arXiv:2502.10325, 2025. — [arXiv:2502.10325](https://arxiv.org/abs/2502.10325) [find](https://scholar.google.com/scholar?q=Sanjiban+Choudhury%2E+Process+reward+models+for+llm+agents%3A+Practical+framework+and+directions%2E+arXiv+preprint+arXiv%3A2502%2E10325%2C+2025%2E+%E2%80%94+%5BarXiv%3A2502%2E10325%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2502%2E10325%29)
47. Yufan Dang, Chen Qian, Xueheng Luo, Jingru Fan, Zihao Xie, Ruijie Shi, Weize Chen, Cheng Yang, Xiaoyin Che, Ye Tian, et al. Multi-agent collaboration via evolving orchestration. arXiv preprint arXiv:2505.19591, 2025. — [arXiv:2505.19591](https://arxiv.org/abs/2505.19591) [find](https://scholar.google.com/scholar?q=Yufan+Dang%2C+Chen+Qian%2C+Xueheng+Luo%2C+Jingru+Fan%2C+Zihao+Xie%2C+Ruijie+Shi%2C+Weize+Chen%2C+Cheng+Yang%2C+Xiaoyin+Che%2C+Ye+Tian%2C+et+al%2E+Multi%2Dagent+collaboration+via+evolving+orchestration%2E+arXiv+preprint+arXiv%3A2)
48. Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. [Mind2web: Towards a generalist agent for the web](https://md.research.elamur.ai/free/en/papers/deng-2023-mind2web-towards-generalist-agent-web/). Advances in Neural Information Processing Systems, 36:28091–28114, 2023.
49. Yihe Deng, Pan Lu, Fan Yin, Ziniu Hu, Sheng Shen, Quanquan Gu, James Y Zou, Kai-Wei Chang, and Wei Wang. Enhancing large vision language models with self-training on image comprehension. Advances in Neural Information Processing Systems, 37:131369–131397, 2024. [find](https://scholar.google.com/scholar?q=Yihe+Deng%2C+Pan+Lu%2C+Fan+Yin%2C+Ziniu+Hu%2C+Sheng+Shen%2C+Quanquan+Gu%2C+James+Y+Zou%2C+Kai%2DWei+Chang%2C+and+Wei+Wang%2E+Enhancing+large+vision+language+models+with+self%2Dtraining+on+image+comprehension%2E+Advances+in+N)
50. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Bert: Bidirectional encoder representations from transformers. arXiv preprint arXiv:1810.[04805, 15, 2018](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/).
51. Guanting Dong, Hongyi Yuan, Keming Lu, Chengpeng Li, Mingfeng Xue, Dayiheng Liu, Wei Wang, Zheng Yuan, Chang Zhou, and Jingren Zhou. [How abilities in large language models are affected by supervised fine-tuning data composition](https://md.research.elamur.ai/free/en/papers/dong-2024-how-abilities-large-language-models/). arXiv preprint arXiv:2310.05492, 2023.
52. Qingxiu Dong, Lei Li, Damai Dai, Ce Zheng, Jingyuan Ma, Rui Li, Heming Xia, Jingjing Xu, Zhiyong Wu, Tianyu Liu, et al. [A survey on in-context learning](https://md.research.elamur.ai/free/en/papers/dong-2023-survey-context-learning/). arXiv preprint arXiv:2301.00234, 2022.
53. Shihan Dou, Ming Zhang, Chenhao Huang, Jiayi Chen, Feng Chen, Shichun Liu, Yan Liu, Chenxiao Liu, Cheng Zhong, Zongzhang Zhang, Tao Gui, Chao Xin, Wei Chengzhi, Lin Yan, Qi Zhang, Yonghui Wu, and Xuanjing Huang. Evalearn: Quantifying the learning capability and efficiency of llms via sequential prob… — [arXiv:2506.02672](https://arxiv.org/abs/2506.02672) [find](https://scholar.google.com/scholar?q=Shihan+Dou%2C+Ming+Zhang%2C+Chenhao+Huang%2C+Jiayi+Chen%2C+Feng+Chen%2C+Shichun+Liu%2C+Yan+Liu%2C+Chenxiao+Liu%2C+Cheng+Zhong%2C+Zongzhang+Zhang%2C+Tao+Gui%2C+Chao+Xin%2C+Wei+Chengzhi%2C+Lin+Yan%2C+Qi+Zhang%2C+Yonghui+Wu%2C+and+Xuan)
54. Yaxin Du, Yuzhu Cai, Yifan Zhou, Cheng Wang, Yu Qian, Xianghe Pang, Qian Liu, Yue Hu, and Siheng Chen. Swe-dev: Evaluating and training autonomous feature-driven software development, 2025. URL https://arxiv.org/abs/2505.16975. — [arXiv:2505.16975](https://arxiv.org/abs/2505.16975) [↗](https://arxiv.org/abs/2505.16975)
55. Zhuoyun Du, Lujie Zheng, Renjun Hu, Yuyang Xu, Xiawei Li, Ying Sun, Wei Chen, Jian Wu, Haolei Cai, and Haohao Ying. [Llms can simulate standardized patients via agent coevolution](https://md.research.elamur.ai/free/en/papers/du-2025-llms-can-simulate-standardized-patients/). arXiv preprint arXiv:2412.11716, 2024.
56. Zhiyu Fan, Kirill Vasilevski, et al. Swe-effi: Re-evaluating software ai agent system effectiveness under resource constraints. arXiv preprint arXiv:2509.09853, 2025. — [arXiv:2509.09853](https://arxiv.org/abs/2509.09853) [find](https://scholar.google.com/scholar?q=Zhiyu+Fan%2C+Kirill+Vasilevski%2C+et+al%2E+Swe%2Deffi%3A+Re%2Devaluating+software+ai+agent+system+effectiveness+under+resource+constraints%2E+arXiv+preprint+arXiv%3A2509%2E09853%2C+2025%2E+%E2%80%94+%5BarXiv%3A2509%2E09853%5D%28https%3A%2F%2Farxi)
57. Junfeng Fang, Houcheng Jiang, Kun Wang, Yunshan Ma, Jie Shi, Xiang Wang, Xiangnan He, and Tat-Seng Chua. Alphaedit: Null-space constrained model editing for language models. In The Thirteenth International Conference on Learning Representations, 2025a. [find](https://scholar.google.com/scholar?q=Junfeng+Fang%2C+Houcheng+Jiang%2C+Kun+Wang%2C+Yunshan+Ma%2C+Jie+Shi%2C+Xiang+Wang%2C+Xiangnan+He%2C+and+Tat%2DSeng+Chua%2E+Alphaedit%3A+Null%2Dspace+constrained+model+editing+for+language+models%2E+In+The+Thirteenth+Internat)
58. Tianqing Fang, Hongming Zhang, Zhisong Zhang, Kaixin Ma, Wenhao Yu, Haitao Mi, and Dong Yu. Webevolver: Enhancing web agent self-improvement with coevolving world model. arXiv preprint arXiv:2504.21024, 2025b. — [arXiv:2504.21024](https://arxiv.org/abs/2504.21024) [find](https://scholar.google.com/scholar?q=Tianqing+Fang%2C+Hongming+Zhang%2C+Zhisong+Zhang%2C+Kaixin+Ma%2C+Wenhao+Yu%2C+Haitao+Mi%2C+and+Dong+Yu%2E+Webevolver%3A+Enhancing+web+agent+self%2Dimprovement+with+coevolving+world+model%2E+arXiv+preprint+arXiv%3A2504%2E2102)
59. Lang Feng, Zhenghai Xue, Tingcong Liu, and Bo An. [Group-in-group policy optimization for llm agent training](https://md.research.elamur.ai/free/en/papers/feng-2025-group-group-policy-optimization-llm/). arXiv preprint arXiv:2505.10978, 2025a.
60. Lang Feng, Zhenghai Xue, Tingcong Liu, and Bo An. [Group-in-group policy optimization for llm agent training](https://md.research.elamur.ai/free/en/papers/feng-2025-group-group-policy-optimization-llm/), 2025b. URL https://arxiv.org/abs/2505.10978. [↗](https://arxiv.org/abs/2505.10978)
61. Yichun Feng, Jiawei Wang, Lu Zhou, and Yixue Li. Doctoragent-rl: A multi-agent collaborative reinforcement learning system for multi-turn clinical dialogue. arXiv preprint arXiv:2505.19630, 2025c. — [arXiv:2505.19630](https://arxiv.org/abs/2505.19630) [find](https://scholar.google.com/scholar?q=Yichun+Feng%2C+Jiawei+Wang%2C+Lu+Zhou%2C+and+Yixue+Li%2E+Doctoragent%2Drl%3A+A+multi%2Dagent+collaborative+reinforcement+learning+system+for+multi%2Dturn+clinical+dialogue%2E+arXiv+preprint+arXiv%3A2505%2E19630%2C+2025c%2E+%E2%80%94+%5B)
62. Chrisantha Fernando, Dylan Banarse, Henryk Michalewski, Simon Osindero, and Tim Rocktäschel. [Promptbreeder: Self-referential self-improvement via prompt evolution](https://md.research.elamur.ai/free/en/papers/fernando-2023-promptbreeder-self-referential-self-improvement/). arXiv preprint arXiv:2309.16797, 2023.
63. Yao Fu, Dong-Ki Kim, Jaekyeom Kim, Sungryull Sohn, Lajanugen Logeswaran, Kyunghoon Bae, and Honglak Lee. Autoguide: Automated generation and selection of state-aware guidelines for large language model agents. arXiv e-prints, pp. arXiv–2403, 2024. [find](https://scholar.google.com/scholar?q=Yao+Fu%2C+Dong%2DKi+Kim%2C+Jaekyeom+Kim%2C+Sungryull+Sohn%2C+Lajanugen+Logeswaran%2C+Kyunghoon+Bae%2C+and+Honglak+Lee%2E+Autoguide%3A+Automated+generation+and+selection+of+state%2Daware+guidelines+for+large+language+mode)
64. Hang Gao and Yongfeng Zhang. PTR: precision-driven tool recommendation for large language models. CoRR, abs/2411.09613, 2024. — [arXiv:2411.09613](https://arxiv.org/abs/2411.09613) [find](https://scholar.google.com/scholar?q=Hang+Gao+and+Yongfeng+Zhang%2E+PTR%3A+precision%2Ddriven+tool+recommendation+for+large+language+models%2E+CoRR%2C+abs%2F2411%2E09613%2C+2024%2E+%E2%80%94+%5BarXiv%3A2411%2E09613%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2411%2E09613%29)
65. Hongcheng Gao, Yue Liu, Yufei He, Longxu Dou, Chao Du, Zhijie Deng, Bryan Hooi, Min Lin, and Tianyu Pang. Flowreasoner: Reinforcing query-level meta-agents. arXiv preprint arXiv:2504.15257, 2025. — [arXiv:2504.15257](https://arxiv.org/abs/2504.15257) [find](https://scholar.google.com/scholar?q=Hongcheng+Gao%2C+Yue+Liu%2C+Yufei+He%2C+Longxu+Dou%2C+Chao+Du%2C+Zhijie+Deng%2C+Bryan+Hooi%2C+Min+Lin%2C+and+Tianyu+Pang%2E+Flowreasoner%3A+Reinforcing+query%2Dlevel+meta%2Dagents%2E+arXiv+preprint+arXiv%3A2504%2E15257%2C+2025%2E+%E2%80%94+%5Ba)
66. Jiaxuan Gao, Shusheng Xu, Wenjie Ye, Weilin Liu, Chuyi He, Wei Fu, Zhiyu Mei, Guangju Wang, and Yi Wu. On designing effective rl reward at training time for llm reasoning. arXiv preprint arXiv:2410.15115, 2024. — [arXiv:2410.15115](https://arxiv.org/abs/2410.15115) [find](https://scholar.google.com/scholar?q=Jiaxuan+Gao%2C+Shusheng+Xu%2C+Wenjie+Ye%2C+Weilin+Liu%2C+Chuyi+He%2C+Wei+Fu%2C+Zhiyu+Mei%2C+Guangju+Wang%2C+and+Yi+Wu%2E+On+designing+effective+rl+reward+at+training+time+for+llm+reasoning%2E+arXiv+preprint+arXiv%3A2410%2E15)
67. Anthony Garuccio. A genetic programming approach to solving optimization problems on agent-based models. Master’s thesis, Duquesne University, 2016. [find](https://scholar.google.com/scholar?q=Anthony+Garuccio%2E+A+genetic+programming+approach+to+solving+optimization+problems+on+agent%2Dbased+models%2E+Master%E2%80%99s+thesis%2C+Duquesne+University%2C+2016%2E)
68. Yingqiang Ge, Wenyue Hua, Kai Mei, Juntao Tan, Shuyuan Xu, Zelong Li, Yongfeng Zhang, et al. Openagi: When llm meets domain experts. Advances in Neural Information Processing Systems, 36:5539–5568, 2023. [find](https://scholar.google.com/scholar?q=Yingqiang+Ge%2C+Wenyue+Hua%2C+Kai+Mei%2C+Juntao+Tan%2C+Shuyuan+Xu%2C+Zelong+Li%2C+Yongfeng+Zhang%2C+et+al%2E+Openagi%3A+When+llm+meets+domain+experts%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%3A5539%E2%80%935568%2C+20)
69. Jiahui Geng, Qing Li, Herbert Woisetschlaeger, Zongxiong Chen, Fengyu Cai, Yuxia Wang, Preslav Nakov, Hans-Arno Jacobsen, and Fakhri Karray. A comprehensive survey of machine unlearning techniques for large language models. arXiv preprint arXiv:2503.01854, 2025a. — [arXiv:2503.01854](https://arxiv.org/abs/2503.01854) [find](https://scholar.google.com/scholar?q=Jiahui+Geng%2C+Qing+Li%2C+Herbert+Woisetschlaeger%2C+Zongxiong+Chen%2C+Fengyu+Cai%2C+Yuxia+Wang%2C+Preslav+Nakov%2C+Hans%2DArno+Jacobsen%2C+and+Fakhri+Karray%2E+A+comprehensive+survey+of+machine+unlearning+techniques+for)
70. Jiayi Geng, Howard Chen, Dilip Arumugam, and Thomas L Griffiths. [Are large language models reliable ai scientists? assessing reverse-engineering of black-box systems](https://md.research.elamur.ai/free/en/papers/geng-2025-large-language-models-reliable/). arXiv preprint arXiv:2505.17968, 2025b.
71. Gaurav Ghosal, Tatsunori Hashimoto, and Aditi Raghunathan. Understanding finetuning for factual knowledge extraction. arXiv preprint arXiv:2406.14785, 2024. — [arXiv:2406.14785](https://arxiv.org/abs/2406.14785) [find](https://scholar.google.com/scholar?q=Gaurav+Ghosal%2C+Tatsunori+Hashimoto%2C+and+Aditi+Raghunathan%2E+Understanding+finetuning+for+factual+knowledge+extraction%2E+arXiv+preprint+arXiv%3A2406%2E14785%2C+2024%2E+%E2%80%94+%5BarXiv%3A2406%2E14785%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F)
72. Ryan Greenblatt, Buck Shlegeris, Kshitij Sachan, and Fabien Roger Sato. Alignment faking in large language models. Anthropic Research, December 2024. URL [https://www.anthropic.com/research/](https://www.anthropic.com/research/) alignment-faking. [↗](https://www.anthropic.com/research/)
73. Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, and Mao Yang. [rstar-math: Small llms can master math reasoning with self-evolved deep thinking](https://md.research.elamur.ai/free/en/papers/guan-2025-rstar-math-small-llms-can/). arXiv preprint arXiv:2501.04519, 2025.
74. Zhenyu Guan, Xiangyu Kong, Fangwei Zhong, and Yizhou Wang. Richelieu: Self-evolving llm-based agents for ai diplomacy. Advances in Neural Information Processing Systems, 37:123471–123497, 2024. [find](https://scholar.google.com/scholar?q=Zhenyu+Guan%2C+Xiangyu+Kong%2C+Fangwei+Zhong%2C+and+Yizhou+Wang%2E+Richelieu%3A+Self%2Devolving+llm%2Dbased+agents+for+ai+diplomacy%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A123471%E2%80%93123497%2C+2024%2E)
75. Dadi Guo, Tianyi Zhou, Dongrui Liu, Chen Qian, Qihan Ren, Shuai Shao, Zhiyuan Fan, Yi R. Fung, Kun Wang, Linfeng Zhang, and Jing Shao. Towards self-evolving benchmarks: Synthesizing agent trajectories via test-time exploration under validate-by-reproduce paradigm. arXiv preprint arXiv:2510.00415, 20… — [arXiv:2510.00415](https://arxiv.org/abs/2510.00415) [find](https://scholar.google.com/scholar?q=Dadi+Guo%2C+Tianyi+Zhou%2C+Dongrui+Liu%2C+Chen+Qian%2C+Qihan+Ren%2C+Shuai+Shao%2C+Zhiyuan+Fan%2C+Yi+R%2E+Fung%2C+Kun+Wang%2C+Linfeng+Zhang%2C+and+Jing+Shao%2E+Towards+self%2Devolving+benchmarks%3A+Synthesizing+agent+trajectories)
76. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948, 2025b.
77. Sheng Guo, Weilin Huang, Haozhi Zhang, Chenfan Zhuang, Dengke Dong, Matthew R Scott, and Dinglong Huang. Curriculumnet: Weakly supervised learning from large-scale web images. In Proceedings of the European conference on computer vision (ECCV), pp. 135–150, 2018. [find](https://scholar.google.com/scholar?q=Sheng+Guo%2C+Weilin+Huang%2C+Haozhi+Zhang%2C+Chenfan+Zhuang%2C+Dengke+Dong%2C+Matthew+R+Scott%2C+and+Dinglong+Huang%2E+Curriculumnet%3A+Weakly+supervised+learning+from+large%2Dscale+web+images%2E+In+Proceedings+of+the+Eu)
78. Dongyoon Hahm, Taywon Min, Woogyeol Jin, and Kimin Lee. Unintended misalignment from agentic fine-tuning: Risks and mitigation. arXiv preprint arXiv:2508.14031, 2025. — [arXiv:2508.14031](https://arxiv.org/abs/2508.14031) [find](https://scholar.google.com/scholar?q=Dongyoon+Hahm%2C+Taywon+Min%2C+Woogyeol+Jin%2C+and+Kimin+Lee%2E+Unintended+misalignment+from+agentic+fine%2Dtuning%3A+Risks+and+mitigation%2E+arXiv+preprint+arXiv%3A2508%2E14031%2C+2025%2E+%E2%80%94+%5BarXiv%3A2508%2E14031%5D%28https%3A%2F%2Farxi)
79. Siwei Han, Jiaqi Liu, Yaofeng Su, Wenbo Duan, Xinyuan Liu, Cihang Xie, Mohit Bansal, Mingyu Ding, Linjun Zhang, and Huaxiu Yao. Alignment tipping process: How self-evolution pushes llm agents off the rails. arXiv preprint arXiv:2510.04860, 2025. [find](https://scholar.google.com/scholar?q=Siwei+Han%2C+Jiaqi+Liu%2C+Yaofeng+Su%2C+Wenbo+Duan%2C+Xinyuan+Liu%2C+Cihang+Xie%2C+Mohit+Bansal%2C+Mingyu+Ding%2C+Linjun+Zhang%2C+and+Huaxiu+Yao%2E+Alignment+tipping+process%3A+How+self%2Devolution+pushes+llm+agents+off+the+)
80. Mohd Ariful Haque, Justin Williams, Sunzida Siddique, Md. Hujaifa Islam, Hasmot Ali, Kishor Datta Gupta, and Roy George. Advanced tool learning and selection system (ATLASS): A closed-loop framework using LLM. CoRR, abs/2503.10071, 2025. — [arXiv:2503.10071](https://arxiv.org/abs/2503.10071) [find](https://scholar.google.com/scholar?q=Mohd+Ariful+Haque%2C+Justin+Williams%2C+Sunzida+Siddique%2C+Md%2E+Hujaifa+Islam%2C+Hasmot+Ali%2C+Kishor+Datta+Gupta%2C+and+Roy+George%2E+Advanced+tool+learning+and+selection+system+%28ATLASS%29%3A+A+closed%2Dloop+framework+u)
81. Moritz Hardt and Yu Sun. Test-time training on nearest neighbors for large language models. arXiv preprint arXiv:2305.18466, 2023. [find](https://scholar.google.com/scholar?q=Moritz+Hardt+and+Yu+Sun%2E+Test%2Dtime+training+on+nearest+neighbors+for+large+language+models%2E+arXiv+preprint+arXiv%3A2305%2E18466%2C+2023%2E)
82. Ami Hauptman and Moshe Sipper. Evolution of an efficient search algorithm for the mate-in-n problem in chess. In European Conference on Genetic Programming, pp. 78–89, 2007. [find](https://scholar.google.com/scholar?q=Ami+Hauptman+and+Moshe+Sipper%2E+Evolution+of+an+efficient+search+algorithm+for+the+mate%2Din%2Dn+problem+in+chess%2E+In+European+Conference+on+Genetic+Programming%2C+pp%2E+78%E2%80%9389%2C+2007%2E)
83. Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, and Dong Yu. [WebVoyager: Building an end-to-end web agent with large multimodal models](https://md.research.elamur.ai/free/en/papers/he-2024-webvoyager-building-end-end-web/). arXiv preprint arXiv:2401.13919, 2024.
84. Yufei He, Ruoyu Li, Alex Chen, Yue Liu, Yulin Chen, Yuan Sui, Cheng Chen, Yi Zhu, Luca Luo, Frank Yang, and Bryan Hooi. Enabling self-improving agents to learn at test time with human-in-the-loop guidance. In Saloni Potdar, Lina Rojas-Barahona, and Sebastien Montella (eds.), Proceedings of the 2025… [find](https://scholar.google.com/scholar?q=Yufei+He%2C+Ruoyu+Li%2C+Alex+Chen%2C+Yue+Liu%2C+Yulin+Chen%2C+Yuan+Sui%2C+Cheng+Chen%2C+Yi+Zhu%2C+Luca+Luo%2C+Frank+Yang%2C+and+Bryan+Hooi%2E+Enabling+self%2Dimproving+agents+to+learn+at+test+time+with+human%2Din%2Dthe%2Dloop+guid)
85. Yufei He, Juncheng Liu, Yue Liu, Yibo Li, Tri Cao, Zhiyuan Hu, Xinxing Xu, and Bryan Hooi. Evotest: Evolutionary test-time learning for self-improving agentic systems. arXiv preprint arXiv:2510.13220, 2025b. — [arXiv:2510.13220](https://arxiv.org/abs/2510.13220) [find](https://scholar.google.com/scholar?q=Yufei+He%2C+Juncheng+Liu%2C+Yue+Liu%2C+Yibo+Li%2C+Tri+Cao%2C+Zhiyuan+Hu%2C+Xinxing+Xu%2C+and+Bryan+Hooi%2E+Evotest%3A+Evolutionary+test%2Dtime+learning+for+self%2Dimproving+agentic+systems%2E+arXiv+preprint+arXiv%3A2510%2E13220%2C)
86. Erik Hemberg, Stephen Moskal, and Una-May O’Reilly. Evolving code with a large language model. Genetic Programming and Evolvable Machines, 25(2):21, 2024. [find](https://scholar.google.com/scholar?q=Erik+Hemberg%2C+Stephen+Moskal%2C+and+Una%2DMay+O%E2%80%99Reilly%2E+Evolving+code+with+a+large+language+model%2E+Genetic+Programming+and+Evolvable+Machines%2C+25%282%29%3A21%2C+2024%2E)
87. John H. Holland. Adaptation in natural and artificial systems, 1976. [find](https://scholar.google.com/scholar?q=John+H%2E+Holland%2E+Adaptation+in+natural+and+artificial+systems%2C+1976%2E)
88. Arian Hosseini, Xingdi Yuan, Nikolay Malkin, Aaron Courville, Alessandro Sordoni, and Rishabh Agarwal. [V-star: Training verifiers for self-taught reasoners](https://md.research.elamur.ai/free/en/papers/hosseini-2024-v-star-training-verifiers-self/). arXiv preprint arXiv:2402.06457, 2024.
89. Mengkang Hu, Yao Mu, Xinmiao Yu, Mingyu Ding, Shiguang Wu, Wenqi Shao, Qiguang Chen, Bin Wang, Yu Qiao, and Ping Luo. Tree-planner: Efficient close-loop task planning with large language models, 2024a. URL https://arxiv.org/abs/2310.08582. — [arXiv:2310.08582](https://arxiv.org/abs/2310.08582) [↗](https://arxiv.org/abs/2310.08582)
90. Mengkang Hu, Pu Zhao, Can Xu, Qingfeng Sun, Jianguang Lou, Qingwei Lin, Ping Luo, and Saravan Rajmohan. Agentgen: Enhancing planning abilities for large language model based agent via environment and task generation. arXiv preprint arXiv:2408.00764, 2024b. — [arXiv:2408.00764](https://arxiv.org/abs/2408.00764) [find](https://scholar.google.com/scholar?q=Mengkang+Hu%2C+Pu+Zhao%2C+Can+Xu%2C+Qingfeng+Sun%2C+Jianguang+Lou%2C+Qingwei+Lin%2C+Ping+Luo%2C+and+Saravan+Rajmohan%2E+Agentgen%3A+Enhancing+planning+abilities+for+large+language+model+based+agent+via+environment+and+)
91. Shengran Hu, Cong Lu, and Jeff Clune. arXiv:2408.[08435, 2024c](https://md.research.elamur.ai/free/en/papers/hu-2024-automated-design-agentic-systems/).
92. [Automated design of agentic systems](https://md.research.elamur.ai/free/en/papers/hu-2024-automated-design-agentic-systems/). arXiv preprint Yuanzhe Hu, Yu Wang, and Julian McAuley. Evaluating memory in llm agents via incremental multi-turn interactions. In ICML 2025 Workshop on Long-Context Foundation Models, 2025.
93. Yue Hu, Yuzhu Cai, Yaxin Du, Xinyu Zhu, Xiangrui Liu, Zijie Yu, Yuchen Hou, Shuo Tang, and Siheng Chen. Self-evolving multi-agent collaboration networks for software development. arXiv preprint arXiv:2410.16946, 2024d. — [arXiv:2410.16946](https://arxiv.org/abs/2410.16946) [find](https://scholar.google.com/scholar?q=Yue+Hu%2C+Yuzhu+Cai%2C+Yaxin+Du%2C+Xinyu+Zhu%2C+Xiangrui+Liu%2C+Zijie+Yu%2C+Yuchen+Hou%2C+Shuo+Tang%2C+and+Siheng+Chen%2E+Self%2Devolving+multi%2Dagent+collaboration+networks+for+software+development%2E+arXiv+preprint+arXiv%3A)
94. Wenyue Hua, Xianjun Yang, Mingyu Jin, Zelong Li, Wei Cheng, Ruixiang Tang, and Yongfeng Zhang. Trustagent: Towards safe and trustworthy llm-based agents through agent constitution. In Trustworthy Multi-modal Foundation Models and AI Agents (TiFA), 2024. [find](https://scholar.google.com/scholar?q=Wenyue+Hua%2C+Xianjun+Yang%2C+Mingyu+Jin%2C+Zelong+Li%2C+Wei+Cheng%2C+Ruixiang+Tang%2C+and+Yongfeng+Zhang%2E+Trustagent%3A+Towards+safe+and+trustworthy+llm%2Dbased+agents+through+agent+constitution%2E+In+Trustworthy+Mult)
95. Baixiang Huang, Zhen Tan, Haoran Wang, Zijie Liu, Dawei Li, Ali Payani, Huan Liu, Tianlong Chen, and Kai Shu. Model editing as a double-edged sword: Steering agent ethical behavior toward beneficence or harm. arXiv preprint arXiv:2506.20606, 2025a. — [arXiv:2506.20606](https://arxiv.org/abs/2506.20606) [find](https://scholar.google.com/scholar?q=Baixiang+Huang%2C+Zhen+Tan%2C+Haoran+Wang%2C+Zijie+Liu%2C+Dawei+Li%2C+Ali+Payani%2C+Huan+Liu%2C+Tianlong+Chen%2C+and+Kai+Shu%2E+Model+editing+as+a+double%2Dedged+sword%3A+Steering+agent+ethical+behavior+toward+beneficence+)
96. Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang, Zongxia Li, Ruosen Li, Jiaxin Huang, Haitao Mi, and Dong Yu. R-zero: Self-evolving reasoning llm from zero data. arXiv preprint arXiv:2508.05004, 2025b. — [arXiv:2508.05004](https://arxiv.org/abs/2508.05004) [find](https://scholar.google.com/scholar?q=Chengsong+Huang%2C+Wenhao+Yu%2C+Xiaoyang+Wang%2C+Hongming+Zhang%2C+Zongxia+Li%2C+Ruosen+Li%2C+Jiaxin+Huang%2C+Haitao+Mi%2C+and+Dong+Yu%2E+R%2Dzero%3A+Self%2Devolving+reasoning+llm+from+zero+data%2E+arXiv+preprint+arXiv%3A2508%2E05)
97. D Huang, JM Zhang, M Luck, Q Bu, Y Qing, and H Cui. Agentcoder: Multi-agent code generation with effective testing and self-optimization. University of Hong Kong, King’s College London, University of Sussex, Shanghai Jiao Tong University, 2024. [find](https://scholar.google.com/scholar?q=D+Huang%2C+JM+Zhang%2C+M+Luck%2C+Q+Bu%2C+Y+Qing%2C+and+H+Cui%2E+Agentcoder%3A+Multi%2Dagent+code+generation+with+effective+testing+and+self%2Doptimization%2E+University+of+Hong+Kong%2C+King%E2%80%99s+College+London%2C+University+of+)
98. Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han. [Large language models can self-improve](https://md.research.elamur.ai/free/en/papers/huang-2023-large-language-models-can-self/). arXiv preprint arXiv:2210.11610, 2022.
99. Jonas Hübotter, Sascha Bongni, Ido Hakimi, and Andreas Krause. Efficiently learning at test-time: Active fine-tuning of llms. arXiv preprint arXiv:2410.08020, 2024. — [arXiv:2410.08020](https://arxiv.org/abs/2410.08020) [find](https://scholar.google.com/scholar?q=Jonas+H%C3%BCbotter%2C+Sascha+Bongni%2C+Ido+Hakimi%2C+and+Andreas+Krause%2E+Efficiently+learning+at+test%2Dtime%3A+Active+fine%2Dtuning+of+llms%2E+arXiv+preprint+arXiv%3A2410%2E08020%2C+2024%2E+%E2%80%94+%5BarXiv%3A2410%2E08020%5D%28https%3A%2F%2Farxiv%2E)
100. Dongwei Jiang, Alvin Zhang, Andrew Wang, Nicholas Andrews, and Daniel Khashabi. Feedback friction: Llms struggle to fully incorporate external feedback. arXiv preprint arXiv:2506.11930, 2025a. — [arXiv:2506.11930](https://arxiv.org/abs/2506.11930) [find](https://scholar.google.com/scholar?q=Dongwei+Jiang%2C+Alvin+Zhang%2C+Andrew+Wang%2C+Nicholas+Andrews%2C+and+Daniel+Khashabi%2E+Feedback+friction%3A+Llms+struggle+to+fully+incorporate+external+feedback%2E+arXiv+preprint+arXiv%3A2506%2E11930%2C+2025a%2E+%E2%80%94+%5BarXi)
101. Lu Jiang, Deyu Meng, Teruko Mitamura, and Alexander G Hauptmann. Easy samples first: Self-paced reranking for zero-example multimedia search. In Proceedings of the 22nd ACM international conference on Multimedia, pp. 547–556, 2014. [find](https://scholar.google.com/scholar?q=Lu+Jiang%2C+Deyu+Meng%2C+Teruko+Mitamura%2C+and+Alexander+G+Hauptmann%2E+Easy+samples+first%3A+Self%2Dpaced+reranking+for+zero%2Dexample+multimedia+search%2E+In+Proceedings+of+the+22nd+ACM+international+conference+on)
102. Yuhua Jiang, Yuwen Xiong, Yufeng Yuan, Chao Xin, Wenyuan Xu, Yu Yue, Qianchuan Zhao, and Lin Yan. [PAG: Multi-turn reinforced llm self-correction with policy as generative verifier](https://md.research.elamur.ai/free/en/papers/jiang-2025-pag-multi-turn-reinforced-llm/). arXiv preprint arXiv:2506.10406, 2025b.
103. Carlos E Jimenez, John Yang, Alexander Wettig, Shunyu Yao, Kexin Pei, Ofir Press, and Karthik Narasimhan. [Swe-bench: Can language models resolve real-world github issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) arXiv preprint arXiv:2310.06770, 2023.
104. Carlos E Jimenez, John Yang, et al. [Swe-bench: Can language models resolve real-world github issues?](https://md.research.elamur.ai/free/en/papers/jimenez-2024-swe-bench-can-language-models/) In ICLR, 2024.
105. Ruofan Jin, Zaixi Zhang, Mengdi Wang, and Le Cong. [Stella: Self-evolving LLM agent for biomedical research](https://md.research.elamur.ai/free/en/papers/jin-2025-stella-self-evolving-llm-agent/). arXiv preprint arXiv:2507.02004, 2025. URL https://arxiv.org/abs/2507.02004. [↗](https://arxiv.org/abs/2507.02004)
106. Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu, Kaixin Ma, Hongming Zhang, Xinya Du, and Dong Yu. [Dsbench: How far are data science agents from becoming data science experts?](https://md.research.elamur.ai/free/en/papers/jing-2024-dsbench-far-data-science-agents/), 2025. URL https://arxiv.org/abs/2409.07703. [↗](https://arxiv.org/abs/2409.07703)
107. Leslie Pack Kaelbling, Michael L Littman, and Andrew W Moore. Reinforcement learning: A survey. Journal of artificial intelligence research, 4:237–285, 1996. [find](https://scholar.google.com/scholar?q=Leslie+Pack+Kaelbling%2C+Michael+L+Littman%2C+and+Andrew+W+Moore%2E+Reinforcement+learning%3A+A+survey%2E+Journal+of+artificial+intelligence+research%2C+4%3A237%E2%80%93285%2C+1996%2E)
108. Zhewei Kang, Xuandong Zhao, and Dawn Song. Scalable best-of-n selection for large language models via self-certainty, 2025. URL https://arxiv.org/abs/2502.18581. [↗](https://arxiv.org/abs/2502.18581)
109. Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen, Caiming Xiong, and Shafiq Joty. Mas-zero: Designing multi-agent systems with zero supervision, 2025. URL https://arxiv.org/abs/2505.14996. — [arXiv:2505.14996](https://arxiv.org/abs/2505.14996) [↗](https://arxiv.org/abs/2505.14996)
110. Omar Khattab, Arnav Singhvi, Paridhi Maheshwari, Zhiyuan Zhang, Keshav Santhanam, Sri Vardhamanan, Saiful Haq, Ashutosh Sharma, Thomas T Joshi, Hanna Moazam, et al. [Dspy: Compiling declarative language model calls into self-improving pipelines](https://md.research.elamur.ai/free/en/papers/khattab-2023-dspy-compiling-declarative-language-model/). arXiv preprint arXiv:2310.03714, 2023.
111. Jiin Kim, Byeongjun Shin, Jinha Chung, and Minsoo Rhu. The cost of dynamic reasoning: Demystifying ai agents and test-time scaling from an ai infrastructure perspective. arXiv preprint arXiv:2506.04301, 2025. — [arXiv:2506.04301](https://arxiv.org/abs/2506.04301) [find](https://scholar.google.com/scholar?q=Jiin+Kim%2C+Byeongjun+Shin%2C+Jinha+Chung%2C+and+Minsoo+Rhu%2E+The+cost+of+dynamic+reasoning%3A+Demystifying+ai+agents+and+test%2Dtime+scaling+from+an+ai+infrastructure+perspective%2E+arXiv+preprint+arXiv%3A2506%2E0430)
112. Louis Kirsch, James Harrison, Daniel Freeman, Jascha Sohl-Dickstein, and Jürgen Schmidhuber. Towards general-purpose in-context learning agents. Workshop on Distribution Shifts, 37th Conference on Neural Information . . . , 2023. [find](https://scholar.google.com/scholar?q=Louis+Kirsch%2C+James+Harrison%2C+Daniel+Freeman%2C+Jascha+Sohl%2DDickstein%2C+and+J%C3%BCrgen+Schmidhuber%2E+Towards+general%2Dpurpose+in%2Dcontext+learning+agents%2E+Workshop+on+Distribution+Shifts%2C+37th+Conference+on+Neu)
113. Woosung Koh, Wonbeen Oh, Jaein Jang, MinHyung Lee, Hyeongjin Kim, Ah Yeon Kim, Joonkee Kim, Junghyun Lee, Taehyeon Kim, and Se-Young Yun. Adastar: Adaptive data sampling for training self-taught reasoners. arXiv preprint arXiv:2505.16322, 2025. — [arXiv:2505.16322](https://arxiv.org/abs/2505.16322) [find](https://scholar.google.com/scholar?q=Woosung+Koh%2C+Wonbeen+Oh%2C+Jaein+Jang%2C+MinHyung+Lee%2C+Hyeongjin+Kim%2C+Ah+Yeon+Kim%2C+Joonkee+Kim%2C+Junghyun+Lee%2C+Taehyeon+Kim%2C+and+Se%2DYoung+Yun%2E+Adastar%3A+Adaptive+data+sampling+for+training+self%2Dtaught+reaso)
114. Harsha Kokel, Michael Katz, Kavitha Srinivas, and Shirin Sohrabi. Acpbench: Reasoning about action, change, and planning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pp. 26559–26568, 2025. [find](https://scholar.google.com/scholar?q=Harsha+Kokel%2C+Michael+Katz%2C+Kavitha+Srinivas%2C+and+Shirin+Sohrabi%2E+Acpbench%3A+Reasoning+about+action%2C+change%2C+and+planning%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+39%2C+p)
115. John R Koza. Human-competitive results produced by genetic programming. Genetic programming and evolvable machines, 11(3):251–284, 2010. [find](https://scholar.google.com/scholar?q=John+R+Koza%2E+Human%2Dcompetitive+results+produced+by+genetic+programming%2E+Genetic+programming+and+evolvable+machines%2C+11%283%29%3A251%E2%80%93284%2C+2010%2E)
116. Aviral Kumar, Rishabh Agarwal, Disha Shrivastava, Feryal Behbahani, Aleksandra Faust, et al. [Training language models to self-correct via reinforcement learning](https://md.research.elamur.ai/free/en/papers/kumar-2024-training-language-models-self-correct/). arXiv preprint arXiv:2409.12917, 2024.
117. Invariant Labs. mcp-scan, 2025. URL [https://github.com/invariantlabs-ai/mcp-scan](https://github.com/invariantlabs-ai/mcp-scan). [↗](https://github.com/invariantlabs-ai/mcp-scan)
118. Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, et al. [Autowebglm: A large language model-based web navigating agent](https://md.research.elamur.ai/free/en/papers/lai-2024-autowebglm-large-language-model-based/). In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 5295–5306,…
119. Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto, Stephen Spencer, Richie Steigerwald, DJ Strouse, Steven Hansen, Angelos Filos, Ethan Brooks, et al. In-context reinforcement learning with algorithm distillation. arXiv preprint arXiv:2210.14215, 2022. — [arXiv:2210.14215](https://arxiv.org/abs/2210.14215) [find](https://scholar.google.com/scholar?q=Michael+Laskin%2C+Luyu+Wang%2C+Junhyuk+Oh%2C+Emilio+Parisotto%2C+Stephen+Spencer%2C+Richie+Steigerwald%2C+DJ+Strouse%2C+Steven+Hansen%2C+Angelos+Filos%2C+Ethan+Brooks%2C+et+al%2E+In%2Dcontext+reinforcement+learning+with+algo)
120. Jonathan Lee, Annie Xie, Aldo Pacchiano, Yash Chandak, Chelsea Finn, Ofir Nachum, and Emma Brunskill. Supervised pretraining can learn in-context reinforcement learning. Advances in Neural Information Processing Systems, 36:43057–43083, 2023. [find](https://scholar.google.com/scholar?q=Jonathan+Lee%2C+Annie+Xie%2C+Aldo+Pacchiano%2C+Yash+Chandak%2C+Chelsea+Finn%2C+Ofir+Nachum%2C+and+Emma+Brunskill%2E+Supervised+pretraining+can+learn+in%2Dcontext+reinforcement+learning%2E+Advances+in+Neural+Information)
121. Ido Levy, Ben Wiesel, Sami Marreed, Alon Oved, Avi Yaeli, and Segev Shlomov. St-webagentbench: A benchmark for evaluating safety and trustworthiness in web agents. arXiv preprint arXiv:2410.06703, 2024. — [arXiv:2410.06703](https://arxiv.org/abs/2410.06703) [find](https://scholar.google.com/scholar?q=Ido+Levy%2C+Ben+Wiesel%2C+Sami+Marreed%2C+Alon+Oved%2C+Avi+Yaeli%2C+and+Segev+Shlomov%2E+St%2Dwebagentbench%3A+A+benchmark+for+evaluating+safety+and+trustworthiness+in+web+agents%2E+arXiv+preprint+arXiv%3A2410%2E06703%2C+202)
122. Hongxin Li, Jingfan Chen, Jingran Su, Yuntao Chen, Qing Li, and Zhaoxiang Zhang. AutoGUI: Scaling gui grounding with automatic functionality annotations from LLMs. arXiv preprint arXiv:2502.01977, 2025a. [find](https://scholar.google.com/scholar?q=Hongxin+Li%2C+Jingfan+Chen%2C+Jingran+Su%2C+Yuntao+Chen%2C+Qing+Li%2C+and+Zhaoxiang+Zhang%2E+AutoGUI%3A+Scaling+gui+grounding+with+automatic+functionality+annotations+from+LLMs%2E+arXiv+preprint+arXiv%3A2502%2E01977%2C+202)
123. Junkai Li, Yunghwei Lai, Weitao Li, Jingyi Ren, Meng Zhang, Xinhui Kang, Siyu Wang, Peng Li, Ya-Qin Zhang, Weizhi Ma, and Yang Liu. Agent hospital: A simulacrum of hospital with evolvable medical agents. arXiv preprint arXiv:2405.02957, 2024a. — [arXiv:2405.02957](https://arxiv.org/abs/2405.02957) [find](https://scholar.google.com/scholar?q=Junkai+Li%2C+Yunghwei+Lai%2C+Weitao+Li%2C+Jingyi+Ren%2C+Meng+Zhang%2C+Xinhui+Kang%2C+Siyu+Wang%2C+Peng+Li%2C+Ya%2DQin+Zhang%2C+Weizhi+Ma%2C+and+Yang+Liu%2E+Agent+hospital%3A+A+simulacrum+of+hospital+with+evolvable+medical+agen)
124. Loka Li, Zhenhao Chen, Guangyi Chen, Yixuan Zhang, Yusheng Su, Eric Xing, and Kun Zhang. Confidence matters: Revisiting intrinsic self-correction capabilities of large language models. arXiv preprint arXiv:2402.12563, 2024b. — [arXiv:2402.12563](https://arxiv.org/abs/2402.12563) [find](https://scholar.google.com/scholar?q=Loka+Li%2C+Zhenhao+Chen%2C+Guangyi+Chen%2C+Yixuan+Zhang%2C+Yusheng+Su%2C+Eric+Xing%2C+and+Kun+Zhang%2E+Confidence+matters%3A+Revisiting+intrinsic+self%2Dcorrection+capabilities+of+large+language+models%2E+arXiv+preprint+)
125. Mengdi Li, Jiaye Lin, Xufeng Zhao, Wenhao Lu, Peilin Zhao, Stefan Wermter, and Di Wang. Curriculum-rlaif: Curriculum alignment with reinforcement learning from ai feedback. arXiv preprint arXiv:2505.20075, 2025b. [find](https://scholar.google.com/scholar?q=Mengdi+Li%2C+Jiaye+Lin%2C+Xufeng+Zhao%2C+Wenhao+Lu%2C+Peilin+Zhao%2C+Stefan+Wermter%2C+and+Di+Wang%2E+Curriculum%2Drlaif%3A+Curriculum+alignment+with+reinforcement+learning+from+ai+feedback%2E+arXiv+preprint+arXiv%3A2505%2E2)
126. Minghao Li, Yingxiu Zhao, Bowen Yu, Feifan Song, Hangyu Li, Haiyang Yu, Zhoujun Li, Fei Huang, and Yongbin Li. [Api-bank: A comprehensive benchmark for tool-augmented llms](https://md.research.elamur.ai/free/en/papers/li-2023-api-bank-comprehensive-benchmark-tool/). arXiv preprint arXiv:2304.08244, 2023.
127. Nathaniel Li, Alexander Pan, Anjali Gopal, Summer Yue, Daniel Berrios, Alice Gatti, Justin D Li, Ann-Kathrin Dombrowski, Shashwat Goel, Long Phan, et al. [The wmdp benchmark: Measuring and reducing malicious use with unlearning](https://md.research.elamur.ai/free/en/papers/li-2024-wmdp-benchmark-measuring-reducing-malicious/). arXiv preprint arXiv:2403.03218, 2024c.
128. Ning Li, Xiangmou Qu, Jiamu Zhou, Jun Wang, Muning Wen, Kounianhua Du, Xingyu Lou, Qiuying Peng, Jun Wang, and Weinan Zhang. MobileUse: A gui agent with hierarchical reflection for autonomous mobile operation. arXiv preprint arXiv:2507.16853, 2025c. — [arXiv:2507.16853](https://arxiv.org/abs/2507.16853) [find](https://scholar.google.com/scholar?q=Ning+Li%2C+Xiangmou+Qu%2C+Jiamu+Zhou%2C+Jun+Wang%2C+Muning+Wen%2C+Kounianhua+Du%2C+Xingyu+Lou%2C+Qiuying+Peng%2C+Jun+Wang%2C+and+Weinan+Zhang%2E+MobileUse%3A+A+gui+agent+with+hierarchical+reflection+for+autonomous+mobile+o)
129. Xiaopeng Li, Pengyue Jia, Derong Xu, Yi Wen, Yingyi Zhang, Wenlin Zhang, Wanyu Wang, Yichao Wang, Zhaocheng Du, Xiangyang Li, et al. A survey of personalization: From rag to agent. arXiv preprint arXiv:2504.10147, 2025d. — [arXiv:2504.10147](https://arxiv.org/abs/2504.10147) [find](https://scholar.google.com/scholar?q=Xiaopeng+Li%2C+Pengyue+Jia%2C+Derong+Xu%2C+Yi+Wen%2C+Yingyi+Zhang%2C+Wenlin+Zhang%2C+Wanyu+Wang%2C+Yichao+Wang%2C+Zhaocheng+Du%2C+Xiangyang+Li%2C+et+al%2E+A+survey+of+personalization%3A+From+rag+to+agent%2E+arXiv+preprint+arXi)
130. Yi-Chen Li, Tian Xu, Yang Yu, Xuqin Zhang, Xiong-Hui Chen, Zhongxiang Ling, Ningjing Chao, Lei Yuan, and Zhi-Hua Zhou. Generalist reward models: Found inside large language models. arXiv preprint arXiv:2506.23235, 2025e. — [arXiv:2506.23235](https://arxiv.org/abs/2506.23235) [find](https://scholar.google.com/scholar?q=Yi%2DChen+Li%2C+Tian+Xu%2C+Yang+Yu%2C+Xuqin+Zhang%2C+Xiong%2DHui+Chen%2C+Zhongxiang+Ling%2C+Ningjing+Chao%2C+Lei+Yuan%2C+and+Zhi%2DHua+Zhou%2E+Generalist+reward+models%3A+Found+inside+large+language+models%2E+arXiv+preprint+arXi)
131. Zelong Li, Shuyuan Xu, Kai Mei, Wenyue Hua, Balaji Rama, Om Raheja, Hao Wang, He Zhu, and Yongfeng Zhang. Autoflow: Automated workflow generation for large language model agents. arXiv preprint arXiv:2407.12821, 2024d. — [arXiv:2407.12821](https://arxiv.org/abs/2407.12821) [find](https://scholar.google.com/scholar?q=Zelong+Li%2C+Shuyuan+Xu%2C+Kai+Mei%2C+Wenyue+Hua%2C+Balaji+Rama%2C+Om+Raheja%2C+Hao+Wang%2C+He+Zhu%2C+and+Yongfeng+Zhang%2E+Autoflow%3A+Automated+workflow+generation+for+large+language+model+agents%2E+arXiv+preprint+arXiv%3A)
132. Xuechen Liang, Yangfan He, Yinghui Xia, Xinyuan Song, Jianhui Wang, Meiling Tao, Li Sun, Xinhang Yuan, Jiayi Su, Keqin Li, Siyuan Chen, and Tianyu Shi. Self-evolving agents with reflective and memory-augmented abilities. arXiv preprint arXiv:2409.00872, 2024. — [arXiv:2409.00872](https://arxiv.org/abs/2409.00872) [find](https://scholar.google.com/scholar?q=Xuechen+Liang%2C+Yangfan+He%2C+Yinghui+Xia%2C+Xinyuan+Song%2C+Jianhui+Wang%2C+Meiling+Tao%2C+Li+Sun%2C+Xinhang+Yuan%2C+Jiayi+Su%2C+Keqin+Li%2C+Siyuan+Chen%2C+and+Tianyu+Shi%2E+Self%2Devolving+agents+with+reflective+and+memory%2D)
133. Junwei Liao, Muning Wen, Jun Wang, and Weinan Zhang. Marft: Multi-agent reinforcement fine-tuning, 2025. URL https://arxiv.org/abs/2504.16129. — [arXiv:2504.16129](https://arxiv.org/abs/2504.16129) [↗](https://arxiv.org/abs/2504.16129)
134. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let’s verify step by step. In The Twelfth International Conference on Learning Representations, 2023. — [Let's Verify Step by Step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/)
135. Bill Yuchen Lin, Yicheng Fu, Karina Yang, Faeze Brahman, Shiyu Huang, Chandra Bhagavatula, Prithviraj Ammanabrolu, Yejin Choi, and Xiang Ren. [Swiftsage: A generative agent with fast and slow thinking for complex interactive tasks](https://md.research.elamur.ai/free/en/papers/lin-2023-swiftsage-generative-agent-fast-slow/). Advances in Neural Information Processing Systems, 36:23813–23825, 20…
136. Chin-Yew Lin. [Rouge: A package for automatic evaluation of summaries](https://md.research.elamur.ai/free/en/papers/lin-2004-rouge-package-automatic-evaluation-summaries/). In Text summarization branches out, pp. 74–81, 2004.
137. Guanyu Lin, Tao Feng, Pengrui Han, Ge Liu, and Jiaxuan You. Arxiv copilot: A self-evolving and efficient LLM system for personalized academic assistance. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 122–130, 2024. URL https://… [find](https://scholar.google.com/scholar?q=Guanyu+Lin%2C+Tao+Feng%2C+Pengrui+Han%2C+Ge+Liu%2C+and+Jiaxuan+You%2E+Arxiv+copilot%3A+A+self%2Devolving+and+efficient+LLM+system+for+personalized+academic+assistance%2E+In+Proceedings+of+the+2024+Conference+on+Empir)
138. Sam Lin, Wenyue Hua, Lingyao Li, Zhenting Wang, and Yongfeng Zhang. Ado: Automatic data optimization for inputs in llm prompts. arXiv preprint arXiv:2502.11436, 2025a. [find](https://scholar.google.com/scholar?q=Sam+Lin%2C+Wenyue+Hua%2C+Lingyao+Li%2C+Zhenting+Wang%2C+and+Yongfeng+Zhang%2E+Ado%3A+Automatic+data+optimization+for+inputs+in+llm+prompts%2E+arXiv+preprint+arXiv%3A2502%2E11436%2C+2025a%2E)
139. Zi Lin, Sheng Shen, Jingbo Shang, Jason Weston, and Yixin Nie. Learning to solve and verify: A self-play framework for code and test generation. arXiv preprint arXiv:2502.14948, 2025b. — [arXiv:2502.14948](https://arxiv.org/abs/2502.14948) [find](https://scholar.google.com/scholar?q=Zi+Lin%2C+Sheng+Shen%2C+Jingbo+Shang%2C+Jason+Weston%2C+and+Yixin+Nie%2E+Learning+to+solve+and+verify%3A+A+self%2Dplay+framework+for+code+and+test+generation%2E+arXiv+preprint+arXiv%3A2502%2E14948%2C+2025b%2E+%E2%80%94+%5BarXiv%3A2502%2E1)
140. Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, Yuheng Cheng, Suyuchen Wang, Xiaoqiang Wang, Yuyu Luo, Haibo Jin, Peiyan Zhang, Ollie Liu, Jiaqi Chen, Huan Zhang, Zhaoyang Yu, Haochen Shi, Boyan Li, Dekun Wu, Fengwei Teng,… — [arXiv:2504.01990](https://arxiv.org/abs/2504.01990) [find](https://scholar.google.com/scholar?q=Bang+Liu%2C+Xinfeng+Li%2C+Jiayi+Zhang%2C+Jinlin+Wang%2C+Tanjin+He%2C+Sirui+Hong%2C+Hongzhang+Liu%2C+Shaokun+Zhang%2C+Kaitao+Song%2C+Kunlun+Zhu%2C+Yuheng+Cheng%2C+Suyuchen+Wang%2C+Xiaoqiang+Wang%2C+Yuyu+Luo%2C+Haibo+Jin%2C+Peiyan+Z)
141. Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, et al. Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary, collaborative, and safe systems. arXiv preprint arXiv:2504.01990, 2025b… — [arXiv:2504.01990](https://arxiv.org/abs/2504.01990) [find](https://scholar.google.com/scholar?q=Bang+Liu%2C+Xinfeng+Li%2C+Jiayi+Zhang%2C+Jinlin+Wang%2C+Tanjin+He%2C+Sirui+Hong%2C+Hongzhang+Liu%2C+Shaokun+Zhang%2C+Kaitao+Song%2C+Kunlun+Zhu%2C+et+al%2E+Advances+and+challenges+in+foundation+agents%3A+From+brain%2Dinspired+i)
142. Ben Liu, Jihan Zhang, Fangquan Lin, Xu Jia, and Min Peng. One size doesn’t fit all: A personalized conversational tutoring agent for mathematics instruction. arXiv preprint arXiv:2502.12633, 2025c. URL https://arxiv.org/abs/2502.12633. — [arXiv:2502.12633](https://arxiv.org/abs/2502.12633) [↗](https://arxiv.org/abs/2502.12633)
143. Bo Liu, Leon Guertler, Simon Yu, Zichen Liu, Penghui Qi, Daniel Balcells, Mickel Liu, Cheston Tan, Weiyan Shi, Min Lin, et al. Spiral: Self-play on zero-sum games incentivizes reasoning via multi-agent multi-turn reinforcement learning. arXiv preprint arXiv:2506.24119, 2025d. — [arXiv:2506.24119](https://arxiv.org/abs/2506.24119) [find](https://scholar.google.com/scholar?q=Bo+Liu%2C+Leon+Guertler%2C+Simon+Yu%2C+Zichen+Liu%2C+Penghui+Qi%2C+Daniel+Balcells%2C+Mickel+Liu%2C+Cheston+Tan%2C+Weiyan+Shi%2C+Min+Lin%2C+et+al%2E+Spiral%3A+Self%2Dplay+on+zero%2Dsum+games+incentivizes+reasoning+via+multi%2Dagen)
144. Dongrui Liu, Huiqi Deng, Xu Cheng, Qihan Ren, Kangrui Wang, and Quanshi Zhang. Towards the difficulty for a deep neural network to learn concepts of different complexities. Advances in Neural Information Processing Systems, 36:41283–41304, 2023a. [find](https://scholar.google.com/scholar?q=Dongrui+Liu%2C+Huiqi+Deng%2C+Xu+Cheng%2C+Qihan+Ren%2C+Kangrui+Wang%2C+and+Quanshi+Zhang%2E+Towards+the+difficulty+for+a+deep+neural+network+to+learn+concepts+of+different+complexities%2E+Advances+in+Neural+Informat)
145. Shaoteng Liu, Haoqi Yuan, Minda Hu, Yanwei Li, Yukang Chen, Shu Liu, Zongqing Lu, and Jiaya Jia. Rl-gpt: Integrating reinforcement learning and code-as-policy. Advances in Neural Information Processing Systems, 37:28430–28459, 2024. [find](https://scholar.google.com/scholar?q=Shaoteng+Liu%2C+Haoqi+Yuan%2C+Minda+Hu%2C+Yanwei+Li%2C+Yukang+Chen%2C+Shu+Liu%2C+Zongqing+Lu%2C+and+Jiaya+Jia%2E+Rl%2Dgpt%3A+Integrating+reinforcement+learning+and+code%2Das%2Dpolicy%2E+Advances+in+Neural+Information+Processin)
146. Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. [Agentbench: Evaluating llms as agents](https://md.research.elamur.ai/free/en/papers/liu-2023-agentbench-evaluating-llms-agents/). arXiv preprint arXiv:2308.03688, 2023b.
147. Yuhang Liu, Pengxiang Li, Congkai Xie, Xavier Hu, Xiaotian Han, Shengyu Zhang, Hongxia Yang, and Fei Wu. Infigui-r1: Advancing multimodal gui agents from reactive actors to deliberative reasoners. arXiv preprint arXiv:2504.14239, 2025e. — [arXiv:2504.14239](https://arxiv.org/abs/2504.14239) [find](https://scholar.google.com/scholar?q=Yuhang+Liu%2C+Pengxiang+Li%2C+Congkai+Xie%2C+Xavier+Hu%2C+Xiaotian+Han%2C+Shengyu+Zhang%2C+Hongxia+Yang%2C+and+Fei+Wu%2E+Infigui%2Dr1%3A+Advancing+multimodal+gui+agents+from+reactive+actors+to+deliberative+reasoners%2E+arX)
148. Yuxuan Liu, Hongda Sun, Wei Liu, Jian Luan, Bo Du, and Rui Yan. Mobilesteward: Integrating multiple app-oriented agents with self-evolution to automate cross-app instructions. arXiv preprint arXiv:2502.16796, 2025f. — [arXiv:2502.16796](https://arxiv.org/abs/2502.16796) [find](https://scholar.google.com/scholar?q=Yuxuan+Liu%2C+Hongda+Sun%2C+Wei+Liu%2C+Jian+Luan%2C+Bo+Du%2C+and+Rui+Yan%2E+Mobilesteward%3A+Integrating+multiple+app%2Doriented+agents+with+self%2Devolution+to+automate+cross%2Dapp+instructions%2E+arXiv+preprint+arXiv%3A250)
149. David Lopez-Paz and Marc’Aurelio Ranzato. Gradient episodic memory for continual learning. In Advances in Neural Information Processing Systems, volume 30, pp. 6467–6476, 2017. [find](https://scholar.google.com/scholar?q=David+Lopez%2DPaz+and+Marc%E2%80%99Aurelio+Ranzato%2E+Gradient+episodic+memory+for+continual+learning%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+30%2C+pp%2E+6467%E2%80%936476%2C+2017%2E)
150. Reza Lotfian and Carlos Busso. Curriculum learning for speech emotion recognition from crowdsourced labels. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(4):815–826, 2019. [find](https://scholar.google.com/scholar?q=Reza+Lotfian+and+Carlos+Busso%2E+Curriculum+learning+for+speech+emotion+recognition+from+crowdsourced+labels%2E+IEEE%2FACM+Transactions+on+Audio%2C+Speech%2C+and+Language+Processing%2C+27%284%29%3A815%E2%80%93826%2C+2019%2E)
151. Jianqiao Lu, Wanjun Zhong, Wenyong Huang, Yufei Wang, Qi Zhu, Fei Mi, Baojun Wang, Weichao Wang, Xingshan Zeng, Lifeng Shang, Xin Jiang, and Qun Liu. SELF: Self-evolution with language feedback. arXiv preprint arXiv:2310.00533, 2023. — [arXiv:2310.00533](https://arxiv.org/abs/2310.00533) [find](https://scholar.google.com/scholar?q=Jianqiao+Lu%2C+Wanjun+Zhong%2C+Wenyong+Huang%2C+Yufei+Wang%2C+Qi+Zhu%2C+Fei+Mi%2C+Baojun+Wang%2C+Weichao+Wang%2C+Xingshan+Zeng%2C+Lifeng+Shang%2C+Xin+Jiang%2C+and+Qun+Liu%2E+SELF%3A+Self%2Devolution+with+language+feedback%2E+arXiv)
152. Jiarui Lu, Thomas Holleis, Yizhe Zhang, Bernhard Aumayer, Feng Nan, Felix Bai, Shuang Ma, Shen Ma, Mengyu Li, Guoli Yin, et al. [Toolsandbox: A stateful, conversational, interactive evaluation benchmark for llm tool use capabilities](https://md.research.elamur.ai/free/en/papers/lu-2025-toolsandbox-stateful-conversational-interactive-evaluation/). arXiv preprint arXiv:2408.04682, 2024a.
153. Junting Lu, Zhiyang Zhang, Fangkai Yang, Jue Zhang, Lu Wang, Chao Du, Qingwei Lin, Saravan Rajmohan, Dongmei Zhang, and Qi Zhang. Axis: Efficient human-agent-computer interaction with api-first llm-based agents. arXiv preprint arXiv:2409.17140, 2024b. [find](https://scholar.google.com/scholar?q=Junting+Lu%2C+Zhiyang+Zhang%2C+Fangkai+Yang%2C+Jue+Zhang%2C+Lu+Wang%2C+Chao+Du%2C+Qingwei+Lin%2C+Saravan+Rajmohan%2C+Dongmei+Zhang%2C+and+Qi+Zhang%2E+Axis%3A+Efficient+human%2Dagent%2Dcomputer+interaction+with+api%2Dfirst+llm%2Dba)
154. Xiaoya Lu, Dongrui Liu, Yi Yu, Luxin Xu, and Jing Shao. X-boundary: Establishing exact safety boundary to shield llms from multi-turn jailbreaks without compromising usability. arXiv preprint arXiv:2502.09990, 2025. — [arXiv:2502.09990](https://arxiv.org/abs/2502.09990) [find](https://scholar.google.com/scholar?q=Xiaoya+Lu%2C+Dongrui+Liu%2C+Yi+Yu%2C+Luxin+Xu%2C+and+Jing+Shao%2E+X%2Dboundary%3A+Establishing+exact+safety+boundary+to+shield+llms+from+multi%2Dturn+jailbreaks+without+compromising+usability%2E+arXiv+preprint+arXiv%3A25)
155. Junyu Luo, Weizhi Zhang, Ye Yuan, Yusheng Zhao, Junwei Yang, Yiyang Gu, Bohan Wu, Binqi Chen, Ziyue Qiao, Qingqing Long, Rongcheng Tu, Xiao Luo, Wei Ju, Zhiping Xiao, Yifan Wang, Meng Xiao, Chenwu Liu, Jingyang Yuan, Shichang Zhang, Yiqiao Jin, Fan Zhang, Xian Wu, Hanqing Zhao, Dacheng Tao, Philip S… — [Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://md.research.elamur.ai/free/en/papers/luo-2025-large-language-model-agent-survey/)
156. Run Luo, Lu Wang, Wanwei He, and Xiaobo Xia. Gui-r1: A generalist r1-style vision-language action model for gui agents. arXiv preprint arXiv:2504.10458, 2025b. — [arXiv:2504.10458](https://arxiv.org/abs/2504.10458) [find](https://scholar.google.com/scholar?q=Run+Luo%2C+Lu+Wang%2C+Wanwei+He%2C+and+Xiaobo+Xia%2E+Gui%2Dr1%3A+A+generalist+r1%2Dstyle+vision%2Dlanguage+action+model+for+gui+agents%2E+arXiv+preprint+arXiv%3A2504%2E10458%2C+2025b%2E+%E2%80%94+%5BarXiv%3A2504%2E10458%5D%28https%3A%2F%2Farxiv%2Eorg%2Fa)
157. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. Self-Refine: Iterative refinement with self-… [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Prakhar+Gupta%2C+Skyler+Hallinan%2C+Luyu+Gao%2C+Sarah+Wiegreffe%2C+Uri+Alon%2C+Nouha+Dziri%2C+Shrimai+Prabhumoye%2C+Yiming+Yang%2C+Shashank+Gupta%2C+Bodhisattwa+Prasad+Majumder%2C+Katherine+Her)
158. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, Shashank Gupta, Bodhisattwa Prasad Majumder, Katherine Hermann, Sean Welleck, Amir Yazdanbakhsh, and Peter Clark. Self-refine: Iterative refinement with self-… [find](https://scholar.google.com/scholar?q=Aman+Madaan%2C+Niket+Tandon%2C+Prakhar+Gupta%2C+Skyler+Hallinan%2C+Luyu+Gao%2C+Sarah+Wiegreffe%2C+Uri+Alon%2C+Nouha+Dziri%2C+Shrimai+Prabhumoye%2C+Yiming+Yang%2C+Shashank+Gupta%2C+Bodhisattwa+Prasad+Majumder%2C+Katherine+Her)
159. Michael McCloskey and Neal J Cohen. Catastrophic interference in connectionist networks: The sequential learning problem. In Psychology of learning and motivation, volume 24, pp. 109–165. Elsevier, 1989. [find](https://scholar.google.com/scholar?q=Michael+McCloskey+and+Neal+J+Cohen%2E+Catastrophic+interference+in+connectionist+networks%3A+The+sequential+learning+problem%2E+In+Psychology+of+learning+and+motivation%2C+volume+24%2C+pp%2E+109%E2%80%93165%2E+Elsevier%2C+19)
160. Ethan Mendes and Alan Ritter. Language models can self-improve at state-value estimation for better search. arXiv preprint arXiv:2503.02878, 2025. — [arXiv:2503.02878](https://arxiv.org/abs/2503.02878) [find](https://scholar.google.com/scholar?q=Ethan+Mendes+and+Alan+Ritter%2E+Language+models+can+self%2Dimprove+at+state%2Dvalue+estimation+for+better+search%2E+arXiv+preprint+arXiv%3A2503%2E02878%2C+2025%2E+%E2%80%94+%5BarXiv%3A2503%2E02878%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503%2E02878)
161. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. [Gaia: a benchmark for general ai assistants](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/). In The Twelfth International Conference on Learning Representations, 2023.
162. Sewon Min, Mike Lewis, Luke Zettlemoyer, and Hannaneh Hajishirzi. Metaicl: Learning to learn in context. arXiv preprint arXiv:2110.15943, 2021. [find](https://scholar.google.com/scholar?q=Sewon+Min%2C+Mike+Lewis%2C+Luke+Zettlemoyer%2C+and+Hannaneh+Hajishirzi%2E+Metaicl%3A+Learning+to+learn+in+context%2E+arXiv+preprint+arXiv%3A2110%2E15943%2C+2021%2E)
163. Amir Moeini, Jiuqi Wang, Jacob Beck, Ethan Blaser, Shimon Whiteson, Rohan Chandra, and Shangtong Zhang. A survey of in-context reinforcement learning. arXiv preprint arXiv:2502.07978, 2025. — [arXiv:2502.07978](https://arxiv.org/abs/2502.07978) [find](https://scholar.google.com/scholar?q=Amir+Moeini%2C+Jiuqi+Wang%2C+Jacob+Beck%2C+Ethan+Blaser%2C+Shimon+Whiteson%2C+Rohan+Chandra%2C+and+Shangtong+Zhang%2E+A+survey+of+in%2Dcontext+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2502%2E07978%2C+2025%2E+%E2%80%94+%5BarXiv%3A2)
164. Thanh Tam Nguyen, Thanh Trung Huynh, Zhao Ren, Phi Le Nguyen, Alan Wee-Chung Liew, Hongzhi Yin, and Quoc Viet Hung Nguyen. A survey of machine unlearning. arXiv preprint arXiv:2209.02299, 2022. — [arXiv:2209.02299](https://arxiv.org/abs/2209.02299) [find](https://scholar.google.com/scholar?q=Thanh+Tam+Nguyen%2C+Thanh+Trung+Huynh%2C+Zhao+Ren%2C+Phi+Le+Nguyen%2C+Alan+Wee%2DChung+Liew%2C+Hongzhi+Yin%2C+and+Quoc+Viet+Hung+Nguyen%2E+A+survey+of+machine+unlearning%2E+arXiv+preprint+arXiv%3A2209%2E02299%2C+2022%2E+%E2%80%94+%5BarX)
165. Kolby Nottingham, Bodhisattwa Prasad Majumder, Bhavana Dalvi Mishra, Sameer Singh, Peter Clark, and Roy Fox. Skill set optimization: Reinforcing language model behavior via transferable skills. In ICML. OpenReview.net, 2024. [find](https://scholar.google.com/scholar?q=Kolby+Nottingham%2C+Bodhisattwa+Prasad+Majumder%2C+Bhavana+Dalvi+Mishra%2C+Sameer+Singh%2C+Peter+Clark%2C+and+Roy+Fox%2E+Skill+set+optimization%3A+Reinforcing+language+model+behavior+via+transferable+skills%2E+In+ICM)
166. Alexander Novikov, Ngân Vũ, Marvin Eisenberger, Emilien Dupont, Po-Sen Huang, Adam Zsolt Wagner, Sergey Shirobokov, Borislav Kozlovskii, Francisco JR Ruiz, Abbas Mehrabian, et al. [Alphaevolve: A coding agent for scientific and algorithmic discovery](https://md.research.elamur.ai/free/en/papers/novikov-2025-alphaevolve-coding-agent-scientific-algorithmic/). arXiv preprint arXiv:2506.13131, 2025.
167. Openai. Introducing swe-bench introducing-swe-bench-verified. verified, 2024. [https://openai.com/index/](https://openai.com/index/) [↗](https://openai.com/index/)
168. Siru Ouyang, Jun Yan, I-Hung Hsu, Yanfei Chen, Ke Jiang, Zifeng Wang, Rujun Han, Long T. Le, Samira Daruki, Xiangru Tang, Vishy Tirumalashetty, George Lee, Mahsan Rofouei, Hangfei Lin, Jiawei Han, Chen-Yu Lee, and Tomas Pfister. Reasoningbank: Scaling agent self-evolving with reasoning memory. arXiv… — [arXiv:2509.25140](https://arxiv.org/abs/2509.25140) [find](https://scholar.google.com/scholar?q=Siru+Ouyang%2C+Jun+Yan%2C+I%2DHung+Hsu%2C+Yanfei+Chen%2C+Ke+Jiang%2C+Zifeng+Wang%2C+Rujun+Han%2C+Long+T%2E+Le%2C+Samira+Daruki%2C+Xiangru+Tang%2C+Vishy+Tirumalashetty%2C+George+Lee%2C+Mahsan+Rofouei%2C+Hangfei+Lin%2C+Jiawei+Han%2C+Che)
169. Yichen Pan, Dehan Kong, Sida Zhou, Cheng Cui, Yifei Leng, Bing Jiang, Hangyu Liu, Yanyi Shang, Shuyan Zhou, Tongshuang Wu, et al. Webcanvas: Benchmarking web agents in online environments. arXiv preprint arXiv:2406.12373, 2024. — [arXiv:2406.12373](https://arxiv.org/abs/2406.12373) [find](https://scholar.google.com/scholar?q=Yichen+Pan%2C+Dehan+Kong%2C+Sida+Zhou%2C+Cheng+Cui%2C+Yifei+Leng%2C+Bing+Jiang%2C+Hangyu+Liu%2C+Yanyi+Shang%2C+Shuyan+Zhou%2C+Tongshuang+Wu%2C+et+al%2E+Webcanvas%3A+Benchmarking+web+agents+in+online+environments%2E+arXiv+prepr)
170. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. [Bleu: a method for automatic evaluation of machine translation](https://md.research.elamur.ai/free/en/papers/papineni-2002-bleu-method-automatic-evaluation-machine/). In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pp. 311–318, 2002.
171. Shubham Parashar, Shurui Gui, Xiner Li, Hongyi Ling, Sushil Vemuri, Blake Olson, Eric Li, Yu Zhang, James Caverlee, Dileep Kalathil, et al. [Curriculum reinforcement learning from easy to hard tasks improves llm reasoning](https://md.research.elamur.ai/free/en/papers/parashar-2025-curriculum-reinforcement-learning-easy-hard/). arXiv preprint arXiv:2506.06632, 2025.
172. German I Parisi, Ronald Kemker, Jose L Part, Christopher Kanan, and Stefan Wermter. [Continual lifelong learning with neural networks: A review](https://md.research.elamur.ai/free/en/papers/parisi-2018-continual-lifelong-learning-neural-networks/). Neural networks, 113:54–71, 2019.
173. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pp. 1–22, 2023. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+O%E2%80%99Brien%2C+Carrie+Jun+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S+Bernstein%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceedings+of+the+36th+ann)
174. Shishir G. Patil, Tianjun Zhang, Xin Wang, and Joseph E. Gonzalez. [Gorilla: Large language model connected with massive apis](https://md.research.elamur.ai/free/en/papers/patil-2023-gorilla-large-language-model-connected/). In NeurIPS, 2024.
175. Joachim Winther Pedersen, Erwan Plantec, Eleni Nisioti, Marcello Barylli, Milton Montero, Kathrin Korte, and Sebastian Risi. Hypernetworks that evolve themselves. In Artificial Life Conference Proceedings 37, volume 2025, pp. 17. MIT Press One Rogers Street, Cambridge, MA 02142-1209, USA journals-in… [find](https://scholar.google.com/scholar?q=Joachim+Winther+Pedersen%2C+Erwan+Plantec%2C+Eleni+Nisioti%2C+Marcello+Barylli%2C+Milton+Montero%2C+Kathrin+Korte%2C+and+Sebastian+Risi%2E+Hypernetworks+that+evolve+themselves%2E+In+Artificial+Life+Conference+Proceed)
176. Dengyun Peng, Yuhang Zhou, Qiguang Chen, Jinhao Liu, Jingjing Chen, and Libo Qin. Dlpo: Towards a robust, efficient, and generalizable prompt optimization framework from a deep-learning perspective. arXiv preprint arXiv:2503.13413, 2025. [find](https://scholar.google.com/scholar?q=Dengyun+Peng%2C+Yuhang+Zhou%2C+Qiguang+Chen%2C+Jinhao+Liu%2C+Jingjing+Chen%2C+and+Libo+Qin%2E+Dlpo%3A+Towards+a+robust%2C+efficient%2C+and+generalizable+prompt+optimization+framework+from+a+deep%2Dlearning+perspective%2E+a)
177. Emmanouil Antonios Platanios, Otilia Stretcu, Graham Neubig, Barnabas Poczos, and Tom M Mitchell. Competence-based curriculum learning for neural machine translation. arXiv preprint arXiv:1903.09848, 2019. [find](https://scholar.google.com/scholar?q=Emmanouil+Antonios+Platanios%2C+Otilia+Stretcu%2C+Graham+Neubig%2C+Barnabas+Poczos%2C+and+Tom+M+Mitchell%2E+Competence%2Dbased+curriculum+learning+for+neural+machine+translation%2E+arXiv+preprint+arXiv%3A1903%2E09848%2C+)
178. Julien Pourcel, Cédric Colas, and Pierre-Yves Oudeyer. Self-improving language models for evolutionary program synthesis: A case study on arc-agi. arXiv preprint arXiv:2507.14172, 2025. — [arXiv:2507.14172](https://arxiv.org/abs/2507.14172) [find](https://scholar.google.com/scholar?q=Julien+Pourcel%2C+C%C3%A9dric+Colas%2C+and+Pierre%2DYves+Oudeyer%2E+Self%2Dimproving+language+models+for+evolutionary+program+synthesis%3A+A+case+study+on+arc%2Dagi%2E+arXiv+preprint+arXiv%3A2507%2E14172%2C+2025%2E+%E2%80%94+%5BarXiv%3A2507%2E)
179. Reid Pryzant, Dan Iter, Jerry Li, Yin Tat Lee, Chenguang Zhu, and Michael Zeng. Automatic prompt optimization with" gradient descent" and beam search. arXiv preprint arXiv:2305.[03495, 2023](https://md.research.elamur.ai/free/en/papers/pryzant-2023-automatic-prompt-optimization-gradient-descent/).
180. Yingming Pu, Tao Lin, and Hongyu Chen. Piflow: Principle-aware scientific discovery with multi-agent collaboration. arXiv preprint arXiv:2505.15047, 2025. — [arXiv:2505.15047](https://arxiv.org/abs/2505.15047) [find](https://scholar.google.com/scholar?q=Yingming+Pu%2C+Tao+Lin%2C+and+Hongyu+Chen%2E+Piflow%3A+Principle%2Daware+scientific+discovery+with+multi%2Dagent+collaboration%2E+arXiv+preprint+arXiv%3A2505%2E15047%2C+2025%2E+%E2%80%94+%5BarXiv%3A2505%2E15047%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F25)
181. Pranav Putta, Edmund Mills, Naman Garg, Sumeet Motwani, Chelsea Finn, Divyansh Garg, and Rafael Rafailov. [Agent q: Advanced reasoning and learning for autonomous ai agents](https://md.research.elamur.ai/free/en/papers/putta-2024-agent-q-advanced-reasoning-learning/). arXiv preprint arXiv:2408.07199, 2024.
182. Zehan Qi, Xiao Liu, Iat Long Iong, Hanyu Lai, Xueqiao Sun, Jiadai Sun, Xinyue Yang, Yu Yang, Shuntian Yao, Wei Xu, Jie Tang, and Yuxiao Dong. Webrl: Training llm web agents via self-evolving online curriculum reinforcement learning. arXiv preprint arXiv:2411.02337, 2024. — [arXiv:2411.02337](https://arxiv.org/abs/2411.02337) [find](https://scholar.google.com/scholar?q=Zehan+Qi%2C+Xiao+Liu%2C+Iat+Long+Iong%2C+Hanyu+Lai%2C+Xueqiao+Sun%2C+Jiadai+Sun%2C+Xinyue+Yang%2C+Yu+Yang%2C+Shuntian+Yao%2C+Wei+Xu%2C+Jie+Tang%2C+and+Yuxiao+Dong%2E+Webrl%3A+Training+llm+web+agents+via+self%2Devolving+online+cu)
183. Chen Qian, Yufan Dang, Jiahao Li, Wei Liu, Zihao Xie, Yifei Wang, Weize Chen, Cheng Yang, Xin Cong, Xiaoyin Che, et al. [Experiential co-learning of software-developing agents](https://md.research.elamur.ai/free/en/papers/qian-2023-experiential-co-learning-software/). arXiv preprint arXiv:2312.17025, 2023a.
184. Cheng Qian, Chi Han, Yi Fung, Yujia Qin, Zhiyuan Liu, and Heng Ji. [CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models](https://md.research.elamur.ai/free/en/papers/qian-2023-creator-tool-creation-disentangling-abstract/). In The 2023 Conference on Empirical Methods in Natural Language Processing, 2023b. URL [https://openreview.net/forum?id=](https://openreview.net/forum?id=) aCHq10rQiH. [↗](https://openreview.net/forum?id=)
185. Cheng Qian, Shihao Liang, Yujia Qin, Yining Ye, Xin Cong, Yankai Lin, Yesai Wu, Zhiyuan Liu, and Maosong Sun. Investigate-consolidate-exploit: A general strategy for inter-task agent self-evolution. arXiv preprint arXiv:2401.13996, 2024a. — [arXiv:2401.13996](https://arxiv.org/abs/2401.13996) [find](https://scholar.google.com/scholar?q=Cheng+Qian%2C+Shihao+Liang%2C+Yujia+Qin%2C+Yining+Ye%2C+Xin+Cong%2C+Yankai+Lin%2C+Yesai+Wu%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+Investigate%2Dconsolidate%2Dexploit%3A+A+general+strategy+for+inter%2Dtask+agent+self%2Devolution%2E+a)
186. Lang Qian, Peng Sun, Yilei Wang, Jiayue Jin, Azzedine Boukerche, and Liang Song. A new online evolu-tive optimization method for driving agents. In GLOBECOM 2024-2024 IEEE Global Communications Conference, pp. 2244–2249. [find](https://scholar.google.com/scholar?q=Lang+Qian%2C+Peng+Sun%2C+Yilei+Wang%2C+Jiayue+Jin%2C+Azzedine+Boukerche%2C+and+Liang+Song%2E+A+new+online+evolu%2Dtive+optimization+method+for+driving+agents%2E+In+GLOBECOM+2024%2D2024+IEEE+Global+Communications+Confer)
187. Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, et al. [Toolllm: Facilitating large language models to master 16000+ real-world apis](https://md.research.elamur.ai/free/en/papers/qin-2023-toolllm-facilitating-large-language-models/). arXiv preprint arXiv:2307.16789, 2023.
188. Jiahao Qiu, Xuan Qi, Hongru Wang, Xinzhe Juan, Yimin Wang, Zelin Zhao, Jiayi Geng, Jiacheng Guo, Peihang Li, Jingzhe Shi, Shilong Liu, and Mengdi Wang. Alita-g: Self-evolving generative agent for agent generation. arXiv preprint arXiv:2510.23601, 2025a. — [arXiv:2510.23601](https://arxiv.org/abs/2510.23601) [find](https://scholar.google.com/scholar?q=Jiahao+Qiu%2C+Xuan+Qi%2C+Hongru+Wang%2C+Xinzhe+Juan%2C+Yimin+Wang%2C+Zelin+Zhao%2C+Jiayi+Geng%2C+Jiacheng+Guo%2C+Peihang+Li%2C+Jingzhe+Shi%2C+Shilong+Liu%2C+and+Mengdi+Wang%2E+Alita%2Dg%3A+Self%2Devolving+generative+agent+for+agen)
189. Jiahao Qiu, Xuan Qi, Tongcheng Zhang, Xinzhe Juan, Jiacheng Guo, Yifu Lu, Yimin Wang, Zixin Yao, Qihan Ren, Xun Jiang, Xing Zhou, Dongrui Liu, Ling Yang, Yue Wu, Kaixuan Huang, Shilong Liu, Hongru Wang, and Mengdi Wang. Alita: Generalist agent enabling scalable agentic reasoning with minimal predefi… — [arXiv:2505.20286](https://arxiv.org/abs/2505.20286) [find](https://scholar.google.com/scholar?q=Jiahao+Qiu%2C+Xuan+Qi%2C+Tongcheng+Zhang%2C+Xinzhe+Juan%2C+Jiacheng+Guo%2C+Yifu+Lu%2C+Yimin+Wang%2C+Zixin+Yao%2C+Qihan+Ren%2C+Xun+Jiang%2C+Xing+Zhou%2C+Dongrui+Liu%2C+Ling+Yang%2C+Yue+Wu%2C+Kaixuan+Huang%2C+Shilong+Liu%2C+Hongru+Wan)
190. Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, and Ji-Rong Wen. Towards completeness-oriented tool retrieval for large language models. In CIKM, pp. 1930–1940. [find](https://scholar.google.com/scholar?q=Changle+Qu%2C+Sunhao+Dai%2C+Xiaochi+Wei%2C+Hengyi+Cai%2C+Shuaiqiang+Wang%2C+Dawei+Yin%2C+Jun+Xu%2C+and+Ji%2DRong+Wen%2E+Towards+completeness%2Doriented+tool+retrieval+for+large+language+models%2E+In+CIKM%2C+pp%2E+1930%E2%80%931940%2E)
191. Changle Qu, Sunhao Dai, Xiaochi Wei, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Jun Xu, and Ji-Rong Wen. From exploration to mastery: Enabling llms to master tools via self-driven interactions. In ICLR. OpenReview.net, 2025. [find](https://scholar.google.com/scholar?q=Changle+Qu%2C+Sunhao+Dai%2C+Xiaochi+Wei%2C+Hengyi+Cai%2C+Shuaiqiang+Wang%2C+Dawei+Yin%2C+Jun+Xu%2C+and+Ji%2DRong+Wen%2E+From+exploration+to+mastery%3A+Enabling+llms+to+master+tools+via+self%2Ddriven+interactions%2E+In+ICLR%2E+)
192. Yuxiao Qu, Tianjun Zhang, Naman Garg, and Aviral Kumar. [Recursive introspection: Teaching language model agents how to self-improve](https://md.research.elamur.ai/free/en/papers/qu-2024-recursive-introspection-teaching-language-model/). Advances in Neural Information Processing Systems, 37:55249–55285, 2024b.
193. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in Neural Information Processing Systems, 36:53728–53741, 2023.
194. Kiran Ramnath, Kang Zhou, Sheng Guan, Soumya Smruti Mishra, Xuan Qi, Zhengyuan Shen, Shuai Wang, Sangmin Woo, Sullam Jeoung, Yawei Wang, et al. [A systematic survey of automatic prompt optimization techniques](https://md.research.elamur.ai/free/en/papers/ramnath-2025-systematic-survey-automatic-prompt-optimization/). arXiv preprint arXiv:2502.16923, 2025.
195. Roger Ratcliff. Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. Psychological review, 97(2):285, 1990. [find](https://scholar.google.com/scholar?q=Roger+Ratcliff%2E+Connectionist+models+of+recognition+memory%3A+constraints+imposed+by+learning+and+forgetting+functions%2E+Psychological+review%2C+97%282%29%3A285%2C+1990%2E)
196. Maxime Robeyns, Martin Szummer, and Laurence Aitchison. A self-improving coding agent. arXiv preprint arXiv:2504.15228, 2025a. — [arXiv:2504.15228](https://arxiv.org/abs/2504.15228) [find](https://scholar.google.com/scholar?q=Maxime+Robeyns%2C+Martin+Szummer%2C+and+Laurence+Aitchison%2E+A+self%2Dimproving+coding+agent%2E+arXiv+preprint+arXiv%3A2504%2E15228%2C+2025a%2E+%E2%80%94+%5BarXiv%3A2504%2E15228%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2504%2E15228%29)
197. Maxime Robeyns, Martin Szummer, and Laurence Aitchison. A self-improving coding agent, 2025b. URL https://arxiv.org/abs/2504.15228. — [arXiv:2504.15228](https://arxiv.org/abs/2504.15228) [↗](https://arxiv.org/abs/2504.15228)
198. David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy Lillicrap, and Gregory Wayne. Experience replay for continual learning. Advances in neural information processing systems, 32, 2019. [find](https://scholar.google.com/scholar?q=David+Rolnick%2C+Arun+Ahuja%2C+Jonathan+Schwarz%2C+Timothy+Lillicrap%2C+and+Gregory+Wayne%2E+Experience+replay+for+continual+learning%2E+Advances+in+neural+information+processing+systems%2C+32%2C+2019%2E)
199. Kai Ruan, Mowen Huang, Ji-Rong Wen, and Hao Sun. Benchmarking llms’ swarm intelligence. arXiv preprint arXiv:2505.04364, 2025. — [arXiv:2505.04364](https://arxiv.org/abs/2505.04364) [find](https://scholar.google.com/scholar?q=Kai+Ruan%2C+Mowen+Huang%2C+Ji%2DRong+Wen%2C+and+Hao+Sun%2E+Benchmarking+llms%E2%80%99+swarm+intelligence%2E+arXiv+preprint+arXiv%3A2505%2E04364%2C+2025%2E+%E2%80%94+%5BarXiv%3A2505%2E04364%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2505%2E04364%29)
200. Rana Salama, Jason Cai, Michelle Yuan, Anna Currey, Monica Sunkara, Yi Zhang, and Yassine Benajiba. [Meminsight: Autonomous memory augmentation for llm agents](https://md.research.elamur.ai/free/en/papers/salama-2025-meminsight-autonomous-memory-augmentation-llm/). arXiv preprint arXiv:2503.21760, 2025.
201. Timo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. [Toolformer: Language models can teach themselves to use tools](https://md.research.elamur.ai/free/en/papers/schick-2023-toolformer-language-models-can-teach/). In NeurIPS, 2023.
202. Sheikh Shafayat, Fahim Tajwar, Ruslan Salakhutdinov, Jeff Schneider, and Andrea Zanette. [Can large reasoning models self-train?](https://md.research.elamur.ai/free/en/papers/shafayat-2025-large-reasoning-models-self-train/), 2025. URL https://arxiv.org/abs/2505.21444. [↗](https://arxiv.org/abs/2505.21444)
203. Lianlei Shan, Shixian Luo, Zezhou Zhu, Yu Yuan, and Yong Wu. Cognitive memory in large language models. arXiv preprint arXiv:2504.02441, 2025. — [arXiv:2504.02441](https://arxiv.org/abs/2504.02441) [find](https://scholar.google.com/scholar?q=Lianlei+Shan%2C+Shixian+Luo%2C+Zezhou+Zhu%2C+Yu+Yuan%2C+and+Yong+Wu%2E+Cognitive+memory+in+large+language+models%2E+arXiv+preprint+arXiv%3A2504%2E02441%2C+2025%2E+%E2%80%94+%5BarXiv%3A2504%2E02441%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2504%2E02441%29)
204. Yu Shang, Yu Li, Keyu Zhao, Likai Ma, Jiahe Liu, Fengli Xu, and Yong Li. Agentsquare: Automatic LLM agent search in modular design space. In ICLR. OpenReview.net, 2025. [find](https://scholar.google.com/scholar?q=Yu+Shang%2C+Yu+Li%2C+Keyu+Zhao%2C+Likai+Ma%2C+Jiahe+Liu%2C+Fengli+Xu%2C+and+Yong+Li%2E+Agentsquare%3A+Automatic+LLM+agent+search+in+modular+design+space%2E+In+ICLR%2E+OpenReview%2Enet%2C+2025%2E)
205. Shuai Shao, Qihan Ren, Chen Qian, Boyi Wei, Dadi Guo, Jingyi Yang, Xinhao Song, Linfeng Zhang, Weinan Zhang, Dongrui Liu, and Jing Shao. Your agent may misevolve: Emergent risks in self-evolving llm agents. arXiv preprint arXiv:2509.26354, 2025. — [arXiv:2509.26354](https://arxiv.org/abs/2509.26354) [find](https://scholar.google.com/scholar?q=Shuai+Shao%2C+Qihan+Ren%2C+Chen+Qian%2C+Boyi+Wei%2C+Dadi+Guo%2C+Jingyi+Yang%2C+Xinhao+Song%2C+Linfeng+Zhang%2C+Weinan+Zhang%2C+Dongrui+Liu%2C+and+Jing+Shao%2E+Your+agent+may+misevolve%3A+Emergent+risks+in+self%2Devolving+llm+a)
206. Yijia Shao, Tianshi Li, Weiyan Shi, Yanchen Liu, and Diyi Yang. Privacylens: Evaluating privacy norm awareness of language models in action. Advances in Neural Information Processing Systems, 37:89373– 89407, 2024a. [find](https://scholar.google.com/scholar?q=Yijia+Shao%2C+Tianshi+Li%2C+Weiyan+Shi%2C+Yanchen+Liu%2C+and+Diyi+Yang%2E+Privacylens%3A+Evaluating+privacy+norm+awareness+of+language+models+in+action%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A89373)
207. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300, 2024b.
208. Ming Shen. Rethinking data selection for supervised fine-tuning. arXiv preprint arXiv:2402.06094, 2024. — [arXiv:2402.06094](https://arxiv.org/abs/2402.06094) [find](https://scholar.google.com/scholar?q=Ming+Shen%2E+Rethinking+data+selection+for+supervised+fine%2Dtuning%2E+arXiv+preprint+arXiv%3A2402%2E06094%2C+2024%2E+%E2%80%94+%5BarXiv%3A2402%2E06094%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2402%2E06094%29)
209. Haizhou Shi, Zihao Xu, Hengyi Wang, Weiyi Qin, Wenyuan Wang, Yibin Wang, Zifeng Wang, Sayna Ebrahimi, and Hao Wang. Continual learning of large language models: A comprehensive survey. ACM Computing Surveys, 2024. [find](https://scholar.google.com/scholar?q=Haizhou+Shi%2C+Zihao+Xu%2C+Hengyi+Wang%2C+Weiyi+Qin%2C+Wenyuan+Wang%2C+Yibin+Wang%2C+Zifeng+Wang%2C+Sayna+Ebrahimi%2C+and+Hao+Wang%2E+Continual+learning+of+large+language+models%3A+A+comprehensive+survey%2E+ACM+Computing+S)
210. Quan Shi, Carlos E Jimenez, Shunyu Yao, Nick Haber, Diyi Yang, and Karthik Narasimhan. When models know more than they can explain: Quantifying knowledge transfer in human-ai collaboration. arXiv preprint arXiv:2506.05579, 2025a. [find](https://scholar.google.com/scholar?q=Quan+Shi%2C+Carlos+E+Jimenez%2C+Shunyu+Yao%2C+Nick+Haber%2C+Diyi+Yang%2C+and+Karthik+Narasimhan%2E+When+models+know+more+than+they+can+explain%3A+Quantifying+knowledge+transfer+in+human%2Dai+collaboration%2E+arXiv+prep)
211. Yucheng Shi, Wenhao Yu, Zaitang Li, Yonglin Wang, Hongming Zhang, Ninghao Liu, Haitao Mi, and Dong Yu. Mobilegui-rl: Advancing mobile gui agent through reinforcement learning in online environment, 2025b. URL https://arxiv.org/abs/2507.05720. — [arXiv:2507.05720](https://arxiv.org/abs/2507.05720) [↗](https://arxiv.org/abs/2507.05720)
212. Zhengliang Shi, Yuhan Wang, Lingyong Yan, Pengjie Ren, Shuaiqiang Wang, Dawei Yin, and Zhaochun Ren. Retrieval models aren’t tool-savvy: Benchmarking tool retrieval for large language models. CoRR, abs/2503.01763, 2025c. [find](https://scholar.google.com/scholar?q=Zhengliang+Shi%2C+Yuhan+Wang%2C+Lingyong+Yan%2C+Pengjie+Ren%2C+Shuaiqiang+Wang%2C+Dawei+Yin%2C+and+Zhaochun+Ren%2E+Retrieval+models+aren%E2%80%99t+tool%2Dsavvy%3A+Benchmarking+tool+retrieval+for+large+language+models%2E+CoRR%2C+ab)
213. Noah Shinn, Federico Cassano, Edward Berman, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. [Reflexion: Language agents with verbal reinforcement learning](https://md.research.elamur.ai/free/en/papers/shinn-2023-reflexion-language-agents-verbal-reinforcement/). In Advances in Neural Information Processing Systems, 2023. URL https://arxiv.org/abs/2303.11366. [↗](https://arxiv.org/abs/2303.11366)
214. David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, et al. [Mastering chess and shogi by self-play with a general reinforcement learning algorithm](https://md.research.elamur.ai/free/en/papers/al-2017-mastering-chess-shogi-self-play/). arXiv preprint arXiv:1712.01815, 2017.
215. Toby Simonds and Akira Yoshiyama. Ladder: Self-improving llms through recursive problem decomposition. arXiv preprint arXiv:2503.00735, 2025. — [arXiv:2503.00735](https://arxiv.org/abs/2503.00735) [find](https://scholar.google.com/scholar?q=Toby+Simonds+and+Akira+Yoshiyama%2E+Ladder%3A+Self%2Dimproving+llms+through+recursive+problem+decomposition%2E+arXiv+preprint+arXiv%3A2503%2E00735%2C+2025%2E+%E2%80%94+%5BarXiv%3A2503%2E00735%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2503%2E00735%29)
216. Toby Simonds, Kevin Lopez, Akira Yoshiyama, and Dominique Garmier. Self rewarding self improving, 2025. URL https://arxiv.org/abs/2505.08827. — [arXiv:2505.08827](https://arxiv.org/abs/2505.08827) [↗](https://arxiv.org/abs/2505.08827)
217. Karl Sims. Evolving virtual creatures. In Proceedings of the 21st Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH ’94, pp. 15–22, New York, NY, USA, 1994. Association for Computing Machinery. ISBN 0897916670. doi: 10.1145/192161.192167. URL https://doi.org/10.1145/192161… — [doi:10.1145/192161.192167](https://doi.org/10.1145/192161.192167) [↗](https://doi.org/10.1145/192161…)
218. Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. [Scaling llm test-time compute optimally can be more effective than scaling model parameters](https://md.research.elamur.ai/free/en/papers/snell-2024-scaling-llm-test-time-compute/). arXiv preprint arXiv:2408.03314, 2024.
219. Kefan Song, Amir Moeini, Peng Wang, Lei Gong, Rohan Chandra, Yanjun Qi, and Shangtong Zhang. Reward is enough: Llms are in-context reinforcement learners. arXiv preprint arXiv:2506.06303, 2025. — [arXiv:2506.06303](https://arxiv.org/abs/2506.06303) [find](https://scholar.google.com/scholar?q=Kefan+Song%2C+Amir+Moeini%2C+Peng+Wang%2C+Lei+Gong%2C+Rohan+Chandra%2C+Yanjun+Qi%2C+and+Shangtong+Zhang%2E+Reward+is+enough%3A+Llms+are+in%2Dcontext+reinforcement+learners%2E+arXiv+preprint+arXiv%3A2506%2E06303%2C+2025%2E+%E2%80%94+%5BarX)
220. Kenneth O Stanley and Risto Miikkulainen. Evolving neural networks through augmenting topologies. Evolutionary computation, 10(2):99–127, 2002. [find](https://scholar.google.com/scholar?q=Kenneth+O+Stanley+and+Risto+Miikkulainen%2E+Evolving+neural+networks+through+augmenting+topologies%2E+Evolutionary+computation%2C+10%282%29%3A99%E2%80%93127%2C+2002%2E)
221. Dimitri Staufer. What should llms forget? quantifying personal data in llms for right-to-be-forgotten requests. arXiv preprint arXiv:2507.11128, 2025. — [arXiv:2507.11128](https://arxiv.org/abs/2507.11128) [find](https://scholar.google.com/scholar?q=Dimitri+Staufer%2E+What+should+llms+forget%3F+quantifying+personal+data+in+llms+for+right%2Dto%2Dbe%2Dforgotten+requests%2E+arXiv+preprint+arXiv%3A2507%2E11128%2C+2025%2E+%E2%80%94+%5BarXiv%3A2507%2E11128%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2507%2E1)
222. Katharina Stein, Daniel Fišer, Jörg Hoffmann, and Alexander Koller. Automating the generation of prompts for llm-based action choice in pddl planning. In Proceedings of the Fourteenth International Conference on Automated Planning and Scheduling (ICAPS 2025). [find](https://scholar.google.com/scholar?q=Katharina+Stein%2C+Daniel+Fi%C5%A1er%2C+J%C3%B6rg+Hoffmann%2C+and+Alexander+Koller%2E+Automating+the+generation+of+prompts+for+llm%2Dbased+action+choice+in+pddl+planning%2E+In+Proceedings+of+the+Fourteenth+International+Co)
223. Hongjin Su, Ruoxi Sun, Jinsung Yoon, Pengcheng Yin, Tao Yu, and Sercan Ö. Arık. Learn-by-interact: A data-centric framework for self-adaptive agents in realistic environments, 2025. URL https://arxiv.org/abs/2501.10893. — [arXiv:2501.10893](https://arxiv.org/abs/2501.10893) [↗](https://arxiv.org/abs/2501.10893)
224. Chuanneng Sun, Songjun Huang, and Dario Pompili. Llm-based multi-agent reinforcement learning: Current and future directions. arXiv preprint arXiv:2405.11106, 2024a. — [arXiv:2405.11106](https://arxiv.org/abs/2405.11106) [find](https://scholar.google.com/scholar?q=Chuanneng+Sun%2C+Songjun+Huang%2C+and+Dario+Pompili%2E+Llm%2Dbased+multi%2Dagent+reinforcement+learning%3A+Current+and+future+directions%2E+arXiv+preprint+arXiv%3A2405%2E11106%2C+2024a%2E+%E2%80%94+%5BarXiv%3A2405%2E11106%5D%28https%3A%2F%2Farxiv)
225. Haochen Sun, Shuwen Zhang, Lujie Niu, Lei Ren, Hao Xu, Hao Fu, Fangkun Zhao, Caixia Yuan, and Xiaojie Wang. Collab-overcooked: Benchmarking and evaluating large language models as collaborative agents. arXiv preprint arXiv:2502.20073, 2025a. [find](https://scholar.google.com/scholar?q=Haochen+Sun%2C+Shuwen+Zhang%2C+Lujie+Niu%2C+Lei+Ren%2C+Hao+Xu%2C+Hao+Fu%2C+Fangkun+Zhao%2C+Caixia+Yuan%2C+and+Xiaojie+Wang%2E+Collab%2Dovercooked%3A+Benchmarking+and+evaluating+large+language+models+as+collaborative+agents)
226. Haotian Sun, Yuchen Zhuang, Lingkai Kong, Bo Dai, and Chao Zhang. [AdaPlanner: Adaptive planning from feedback with language models](https://md.research.elamur.ai/free/en/papers/sun-2023-adaplanner-adaptive-planning-feedback-language/). In Advances in Neural Information Processing Systems, 2023. URL [https://openreview.net/forum?id=rnKgbKmelt](https://openreview.net/forum?id=rnKgbKmelt). [↗](https://openreview.net/forum?id=rnKgbKmelt)
227. Qiushi Sun, Kanzhi Cheng, Zichen Ding, Chuanyang Jin, Yian Wang, Fangzhi Xu, Zhenyu Wu, Chengyou Jia, Liheng Chen, Zhoumianze Liu, et al. [Os-genesis: Automating gui agent trajectory construction via reverse task synthesis](https://md.research.elamur.ai/free/en/papers/sun-2025-os-genesis-automating-gui-agent/). arXiv preprint arXiv:2412.19723, 2024b.
228. Qiushi Sun, Mukai Li, Zhoumianze Liu, Zhihui Xie, Fangzhi Xu, Zhangyue Yin, Kanzhi Cheng, Zehao Li, Zichen Ding, Qi Liu, et al. [Os-sentinel: Towards safety-enhanced mobile gui agents via hybrid validation in realistic workflows](https://md.research.elamur.ai/free/en/papers/sun-2026-os-sentinel-safety-enhanced-mobile/). arXiv preprint arXiv:2510.24411, 2025b.
229. Zeyi Sun, Ziyu Liu, Yuhang Zang, Yuhang Cao, Xiaoyi Dong, Tong Wu, Dahua Lin, and Jiaqi Wang. Seagent: Self-evolving computer use agent with autonomous learning from experience. arXiv preprint arXiv:2508.04700, 2025c. — [arXiv:2508.04700](https://arxiv.org/abs/2508.04700) [find](https://scholar.google.com/scholar?q=Zeyi+Sun%2C+Ziyu+Liu%2C+Yuhang+Zang%2C+Yuhang+Cao%2C+Xiaoyi+Dong%2C+Tong+Wu%2C+Dahua+Lin%2C+and+Jiaqi+Wang%2E+Seagent%3A+Self%2Devolving+computer+use+agent+with+autonomous+learning+from+experience%2E+arXiv+preprint+arXiv%3A2)
230. Heng Tang, Feng Liu, Xinbo Chen, Jiawei Chen, Bohao Wang, Changwang Zhang, Jun Wang, Yuegang Sun, Bingde Hu, and Can Wang. Bridging the gap: Self-optimized fine-tuning for llm-based recommender systems. arXiv preprint arXiv:2505.20771, 2025. — [arXiv:2505.20771](https://arxiv.org/abs/2505.20771) [find](https://scholar.google.com/scholar?q=Heng+Tang%2C+Feng+Liu%2C+Xinbo+Chen%2C+Jiawei+Chen%2C+Bohao+Wang%2C+Changwang+Zhang%2C+Jun+Wang%2C+Yuegang+Sun%2C+Bingde+Hu%2C+and+Can+Wang%2E+Bridging+the+gap%3A+Self%2Doptimized+fine%2Dtuning+for+llm%2Dbased+recommender+system)
231. Qiaoyu Tang, Ziliang Deng, Hongyu Lin, Xianpei Han, Qiao Liang, Boxi Cao, and Le Sun. [Toolalpaca: Generalized tool learning for language models with 3000 simulated cases](https://md.research.elamur.ai/free/en/papers/tang-2023-toolalpaca-generalized-tool-learning-language/). arXiv preprint arXiv:2306.05301, 2023.
232. Zhengwei Tao, Ting-En Lin, Xiancai Chen, Hangyu Li, Yuchuan Wu, Yongbin Li, Zhi Jin, Fei Huang, Dacheng Tao, and Jingren Zhou. A survey on self-evolution of large language models. arXiv preprint arXiv:2404.14387, 2024. — [arXiv:2404.14387](https://arxiv.org/abs/2404.14387) [find](https://scholar.google.com/scholar?q=Zhengwei+Tao%2C+Ting%2DEn+Lin%2C+Xiancai+Chen%2C+Hangyu+Li%2C+Yuchuan+Wu%2C+Yongbin+Li%2C+Zhi+Jin%2C+Fei+Huang%2C+Dacheng+Tao%2C+and+Jingren+Zhou%2E+A+survey+on+self%2Devolution+of+large+language+models%2E+arXiv+preprint+arXiv)
233. Amir Taubenfeld, Tom Sheffer, Eran Ofek, Amir Feder, Ariel Goldstein, Zorik Gekhman, and Gal Yona. Confidence improves self-consistency in llms. arXiv preprint arXiv:2502.06233, 2025. [find](https://scholar.google.com/scholar?q=Amir+Taubenfeld%2C+Tom+Sheffer%2C+Eran+Ofek%2C+Amir+Feder%2C+Ariel+Goldstein%2C+Zorik+Gekhman%2C+and+Gal+Yona%2E+Confidence+improves+self%2Dconsistency+in+llms%2E+arXiv+preprint+arXiv%3A2502%2E06233%2C+2025%2E)
234. Yi Tay, Shuohang Wang, Luu Anh Tuan, Jie Fu, Minh C Phan, Xingdi Yuan, Jinfeng Rao, Siu Cheung Hui, and Aston Zhang. Simple and effective curriculum pointer-generator networks for reading comprehension over long narratives. arXiv preprint arXiv:1905.10847, 2019. [find](https://scholar.google.com/scholar?q=Yi+Tay%2C+Shuohang+Wang%2C+Luu+Anh+Tuan%2C+Jie+Fu%2C+Minh+C+Phan%2C+Xingdi+Yuan%2C+Jinfeng+Rao%2C+Siu+Cheung+Hui%2C+and+Aston+Zhang%2E+Simple+and+effective+curriculum+pointer%2Dgenerator+networks+for+reading+comprehensio)
235. Patara Trirat, Wonyong Jeong, and Sung Ju Hwang. Agentic predictor: Performance prediction for agentic workflows via multi-view encoding. arXiv preprint arXiv:2505.19764, 2025. — [arXiv:2505.19764](https://arxiv.org/abs/2505.19764) [find](https://scholar.google.com/scholar?q=Patara+Trirat%2C+Wonyong+Jeong%2C+and+Sung+Ju+Hwang%2E+Agentic+predictor%3A+Performance+prediction+for+agentic+workflows+via+multi%2Dview+encoding%2E+arXiv+preprint+arXiv%3A2505%2E19764%2C+2025%2E+%E2%80%94+%5BarXiv%3A2505%2E19764%5D%28ht)
236. Keyon Vafa, Peter G Chang, Ashesh Rambachan, and Sendhil Mullainathan. What has a foundation model found? using inductive bias to probe for world models. arXiv preprint arXiv:2507.06952, 2025. — [arXiv:2507.06952](https://arxiv.org/abs/2507.06952) [find](https://scholar.google.com/scholar?q=Keyon+Vafa%2C+Peter+G+Chang%2C+Ashesh+Rambachan%2C+and+Sendhil+Mullainathan%2E+What+has+a+foundation+model+found%3F+using+inductive+bias+to+probe+for+world+models%2E+arXiv+preprint+arXiv%3A2507%2E06952%2C+2025%2E+%E2%80%94+%5BarXi)
237. Karthik Valmeekam, Matthew Marquez, Alberto Olmo, Sarath Sreedharan, and Subbarao Kambhampati. [Planbench: An extensible benchmark for evaluating large language models on planning and reasoning about change](https://md.research.elamur.ai/free/en/papers/valmeekam-2022-planbench-extensible-benchmark-evaluating-large/). Advances in Neural Information Processing Systems, 36:38975–38987, 2023.
238. Luanbo Wan and Weizhi Ma. Storybench: A dynamic benchmark for evaluating long-term memory with multi turns. arXiv preprint arXiv:2506.13356, 2025. — [arXiv:2506.13356](https://arxiv.org/abs/2506.13356) [find](https://scholar.google.com/scholar?q=Luanbo+Wan+and+Weizhi+Ma%2E+Storybench%3A+A+dynamic+benchmark+for+evaluating+long%2Dterm+memory+with+multi+turns%2E+arXiv+preprint+arXiv%3A2506%2E13356%2C+2025%2E+%E2%80%94+%5BarXiv%3A2506%2E13356%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E13356)
239. Ziyu Wan, Yunxiang Li, Xiaoyu Wen, Yan Song, Hanjing Wang, Linyi Yang, Mark Schmidt, Jun Wang, Weinan Zhang, Shuyue Hu, and Ying Wen. Rema: Learning to meta-think for llms with multi-agent reinforcement learning, 2025. URL https://arxiv.org/abs/2503.09501. — [arXiv:2503.09501](https://arxiv.org/abs/2503.09501) [↗](https://arxiv.org/abs/2503.09501)
240. Bin Wang, Zexin Liu, Hao Yu, Ao Yang, Yenan Huang, Jing Guo, Huangsheng Cheng, Hui Li, and Huiyu Wu. Mcpguard: Automatically detecting vulnerabilities in mcp servers. arXiv preprint arXiv:2510.23673, 2025a. — [arXiv:2510.23673](https://arxiv.org/abs/2510.23673) [find](https://scholar.google.com/scholar?q=Bin+Wang%2C+Zexin+Liu%2C+Hao+Yu%2C+Ao+Yang%2C+Yenan+Huang%2C+Jing+Guo%2C+Huangsheng+Cheng%2C+Hui+Li%2C+and+Huiyu+Wu%2E+Mcpguard%3A+Automatically+detecting+vulnerabilities+in+mcp+servers%2E+arXiv+preprint+arXiv%3A2510%2E23673%2C+)
241. Bo Wang, Weiyi He, Pengfei He, Shenglai Zeng, Zhen Xiang, Yue Xing, and Jiliang Tang. [Unveiling privacy risks in llm agent memory](https://md.research.elamur.ai/free/en/papers/wang-2025-unveiling-privacy-risks-llm-agent/). arXiv preprint arXiv:2502.13172, 2025b.
242. Borui Wang, Kathleen McKeown, and Rex Ying. Dystil: Dynamic strategy induction with large language models for reinforcement learning, 2025c. URL https://arxiv.org/abs/2505.03209. — [arXiv:2505.03209](https://arxiv.org/abs/2505.03209) [↗](https://arxiv.org/abs/2505.03209)
243. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291, 2023a. [find](https://scholar.google.com/scholar?q=Guanzhi+Wang%2C+Yuqi+Xie%2C+Yunfan+Jiang%2C+Ajay+Mandlekar%2C+Chaowei+Xiao%2C+Yuke+Zhu%2C+Linxi+Fan%2C+and+Anima+Anandkumar%2E+Voyager%3A+An+open%2Dended+embodied+agent+with+large+language+models%2E+arXiv+preprint+arXiv%3A23)
244. Hanlin Wang, Chak Tou Leong, Jiashuo Wang, Jian Wang, and Wenjie Li. Spa-rl: Reinforcing llm agents via stepwise progress attribution. arXiv preprint arXiv:2505.20732, 2025d. — [arXiv:2505.20732](https://arxiv.org/abs/2505.20732) [find](https://scholar.google.com/scholar?q=Hanlin+Wang%2C+Chak+Tou+Leong%2C+Jiashuo+Wang%2C+Jian+Wang%2C+and+Wenjie+Li%2E+Spa%2Drl%3A+Reinforcing+llm+agents+via+stepwise+progress+attribution%2E+arXiv+preprint+arXiv%3A2505%2E20732%2C+2025d%2E+%E2%80%94+%5BarXiv%3A2505%2E20732%5D%28http)
245. Haoyu Wang, Dong Fang, et al. Fela: A multi-agent evolutionary system for feature engineering of industrial event log data. arXiv preprint arXiv:2510.25223, 2025e. — [arXiv:2510.25223](https://arxiv.org/abs/2510.25223) [find](https://scholar.google.com/scholar?q=Haoyu+Wang%2C+Dong+Fang%2C+et+al%2E+Fela%3A+A+multi%2Dagent+evolutionary+system+for+feature+engineering+of+industrial+event+log+data%2E+arXiv+preprint+arXiv%3A2510%2E25223%2C+2025e%2E+%E2%80%94+%5BarXiv%3A2510%2E25223%5D%28https%3A%2F%2Farxiv%2Eo)
246. Hongru Wang, Yujia Qin, Yankai Lin, Jeff Z. Pan, and Kam-Fai Wong. Empowering large language models: Tool learning for real-world interaction. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’24, pp. 2983–2986, New York, NY, U… — [doi:10.1145/3626772.3661381](https://doi.org/10.1145/3626772.3661381) [find](https://scholar.google.com/scholar?q=Hongru+Wang%2C+Yujia+Qin%2C+Yankai+Lin%2C+Jeff+Z%2E+Pan%2C+and+Kam%2DFai+Wong%2E+Empowering+large+language+models%3A+Tool+learning+for+real%2Dworld+interaction%2E+In+Proceedings+of+the+47th+International+ACM+SIGIR+Confer)
247. Hongru Wang, Rui Wang, Boyang Xue, Heming Xia, Jingtao Cao, Zeming Liu, Jeff Z. Pan, and Kam-Fai Wong. AppBench: Planning of multiple APIs from various APPs for complex user instruction. In Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen (eds.), Proceedings of the 2024 Conference on Empirical Meth… [find](https://scholar.google.com/scholar?q=Hongru+Wang%2C+Rui+Wang%2C+Boyang+Xue%2C+Heming+Xia%2C+Jingtao+Cao%2C+Zeming+Liu%2C+Jeff+Z%2E+Pan%2C+and+Kam%2DFai+Wong%2E+AppBench%3A+Planning+of+multiple+APIs+from+various+APPs+for+complex+user+instruction%2E+In+Yaser+Al%2DO)
248. Hongru Wang, Deng Cai, Wanjun Zhong, Shijue Huang, Jeff Z. Pan, Zeming Liu, and Kam-Fai Wong. Self-reasoning language models: Unfold hidden reasoning chains with few reasoning catalyst, 2025f. URL https://arxiv.org/abs/2505.14116. [↗](https://arxiv.org/abs/2505.14116)
249. Hongru Wang, Cheng Qian, Manling Li, Jiahao Qiu, Boyang Xue, Mengdi Wang, Heng Ji, and Kam-Fai Wong. Toward a theory of agents as tool-use decision-makers, 2025g. URL https://arxiv.org/abs/ 2506.00886. [↗](https://arxiv.org/abs/)
250. Hongru Wang, Cheng Qian, Jiahao Qiu, et al. OTC-PO: Optimal tool calls via reinforcement learning. arXiv preprint arXiv:2504.14870, 2025h. — [arXiv:2504.14870](https://arxiv.org/abs/2504.14870) [find](https://scholar.google.com/scholar?q=Hongru+Wang%2C+Cheng+Qian%2C+Jiahao+Qiu%2C+et+al%2E+OTC%2DPO%3A+Optimal+tool+calls+via+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2504%2E14870%2C+2025h%2E+%E2%80%94+%5BarXiv%3A2504%2E14870%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2504%2E14870%29)
251. Kun Wang, Guibin Zhang, Zhenhong Zhou, Jiahao Wu, Miao Yu, Shiqian Zhao, Chenlong Yin, Jinhu Fu, Yibo Yan, Hanjun Luo, et al. A comprehensive survey in llm (-agent) full stack safety: Data, training and deployment. arXiv preprint arXiv:2504.15585, 2025i. — [arXiv:2504.15585](https://arxiv.org/abs/2504.15585) [find](https://scholar.google.com/scholar?q=Kun+Wang%2C+Guibin+Zhang%2C+Zhenhong+Zhou%2C+Jiahao+Wu%2C+Miao+Yu%2C+Shiqian+Zhao%2C+Chenlong+Yin%2C+Jinhu+Fu%2C+Yibo+Yan%2C+Hanjun+Luo%2C+et+al%2E+A+comprehensive+survey+in+llm+%28%2Dagent%29+full+stack+safety%3A+Data%2C+training+a)
252. Liyuan Wang, Xingxing Zhang, Hang Su, and Jun Zhu. A comprehensive survey of continual learning: Theory, method and application. IEEE transactions on pattern analysis and machine intelligence, 46(8): 5362–5383, 2024c. [find](https://scholar.google.com/scholar?q=Liyuan+Wang%2C+Xingxing+Zhang%2C+Hang+Su%2C+and+Jun+Zhu%2E+A+comprehensive+survey+of+continual+learning%3A+Theory%2C+method+and+application%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence%2C+46%288%29%3A+)
253. Peiyi Wang, Lei Li, Zhihong Shao, RX Xu, Damai Dai, Yifei Li, Deli Chen, Yu Wu, and Zhifang Sui. [Math-shepherd: Verify and reinforce llms step-by-step without human annotations](https://md.research.elamur.ai/free/en/papers/wang-2024-math-shepherd-verify-reinforce-llms/). arXiv preprint arXiv:2312.08935, 2023b.
254. Peng Wang, Ruihan Tao, Qiguang Chen, Mengkang Hu, and Libo Qin. X-webagentbench: A multilingual interactive web benchmark for evaluating global agentic system. arXiv preprint arXiv:2505.15372, 2025j. [find](https://scholar.google.com/scholar?q=Peng+Wang%2C+Ruihan+Tao%2C+Qiguang+Chen%2C+Mengkang+Hu%2C+and+Libo+Qin%2E+X%2Dwebagentbench%3A+A+multilingual+interactive+web+benchmark+for+evaluating+global+agentic+system%2E+arXiv+preprint+arXiv%3A2505%2E15372%2C+2025j%2E)
255. Renxi Wang, Xudong Han, Lei Ji, Shu Wang, Timothy Baldwin, and Haonan Li. Toolgen: Unified tool retrieval and calling via generation. In ICLR. OpenReview.net, 2025k. [find](https://scholar.google.com/scholar?q=Renxi+Wang%2C+Xudong+Han%2C+Lei+Ji%2C+Shu+Wang%2C+Timothy+Baldwin%2C+and+Haonan+Li%2E+Toolgen%3A+Unified+tool+retrieval+and+calling+via+generation%2E+In+ICLR%2E+OpenReview%2Enet%2C+2025k%2E)
256. Rui Wang, Ce Zhang, Jun-Yu Ma, Jianshu Zhang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu, and Kam-Fai Wong. Explore to evolve: Scaling evolved aggregation logic via proactive online exploration for deep research agents. arXiv preprint arXiv:251… — [arXiv:2510.14438](https://arxiv.org/abs/2510.14438) [find](https://scholar.google.com/scholar?q=Rui+Wang%2C+Ce+Zhang%2C+Jun%2DYu+Ma%2C+Jianshu+Zhang%2C+Hongru+Wang%2C+Yi+Chen%2C+Boyang+Xue%2C+Tianqing+Fang%2C+Zhisong+Zhang%2C+Hongming+Zhang%2C+Haitao+Mi%2C+Dong+Yu%2C+and+Kam%2DFai+Wong%2E+Explore+to+evolve%3A+Scaling+evolved+a)
257. Saizhuo Wang, Hang Yuan, Lionel M Ni, and Jian Guo. [Quantagent: Seeking holy grail in trading by self-improving large language model](https://md.research.elamur.ai/free/en/papers/wang-2024-quantagent-seeking-holy-grail-trading/). arXiv preprint arXiv:2402.03755, 2024d.
258. Shaobo Wang, Zhengbo Jiao, Zifan Zhang, Yilang Peng, Xu Ze, Boyu Yang, Wei Wang, Hu Wei, and Linfeng Zhang. Socratic-zero: Bootstrapping reasoning via data-free agent co-evolution. arXiv preprint arXiv:2509.24726, 2025m. — [arXiv:2509.24726](https://arxiv.org/abs/2509.24726) [find](https://scholar.google.com/scholar?q=Shaobo+Wang%2C+Zhengbo+Jiao%2C+Zifan+Zhang%2C+Yilang+Peng%2C+Xu+Ze%2C+Boyu+Yang%2C+Wei+Wang%2C+Hu+Wei%2C+and+Linfeng+Zhang%2E+Socratic%2Dzero%3A+Bootstrapping+reasoning+via+data%2Dfree+agent+co%2Devolution%2E+arXiv+preprint+arXi)
259. Siyuan Wang, Zhuohan Long, Zhihao Fan, Zhongyu Wei, and Xuanjing Huang. [Benchmark self-evolving: A multi-agent framework for dynamic llm evaluation](https://md.research.elamur.ai/free/en/papers/wang-2025-benchmark-self-evolving-multi-agent/). arXiv preprint arXiv:2402.11443, 2024e.
260. Song Wang, Yaochen Zhu, Haochen Liu, Zaiyi Zheng, Chen Chen, and Jundong Li. Knowledge editing for [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). ACM Computing Surveys, 57(3):1–37, 2024f.
261. Taiyi Wang, Zhihao Wu, Jianheng Liu, Jianye Hao, Jun Wang, and Kun Shao. Distrl: An asynchronous distributed reinforcement learning framework for on-device control agents. arXiv preprint arXiv:2410.14803, 2024g. — [arXiv:2410.14803](https://arxiv.org/abs/2410.14803) [find](https://scholar.google.com/scholar?q=Taiyi+Wang%2C+Zhihao+Wu%2C+Jianheng+Liu%2C+Jianye+Hao%2C+Jun+Wang%2C+and+Kun+Shao%2E+Distrl%3A+An+asynchronous+distributed+reinforcement+learning+framework+for+on%2Ddevice+control+agents%2E+arXiv+preprint+arXiv%3A2410%2E14)
262. Tevin Wang and Chenyan Xiong. Autorule: Reasoning chain-of-thought extracted rule-based rewards improve preference learning. arXiv preprint arXiv:2506.15651, 2025. — [arXiv:2506.15651](https://arxiv.org/abs/2506.15651) [find](https://scholar.google.com/scholar?q=Tevin+Wang+and+Chenyan+Xiong%2E+Autorule%3A+Reasoning+chain%2Dof%2Dthought+extracted+rule%2Dbased+rewards+improve+preference+learning%2E+arXiv+preprint+arXiv%3A2506%2E15651%2C+2025%2E+%E2%80%94+%5BarXiv%3A2506%2E15651%5D%28https%3A%2F%2Farxiv%2Eo)
263. Xiao Wang, Yuansen Zhang, Tianze Chen, Songyang Gao, Senjie Jin, Xianjun Yang, Zhiheng Xi, Rui Zheng, Yicheng Zou, Tao Gui, et al. Trace: A comprehensive benchmark for continual learning in large language models. arXiv preprint arXiv:2310.06762, 2023c. — [arXiv:2310.06762](https://arxiv.org/abs/2310.06762) [find](https://scholar.google.com/scholar?q=Xiao+Wang%2C+Yuansen+Zhang%2C+Tianze+Chen%2C+Songyang+Gao%2C+Senjie+Jin%2C+Xianjun+Yang%2C+Zhiheng+Xi%2C+Rui+Zheng%2C+Yicheng+Zou%2C+Tao+Gui%2C+et+al%2E+Trace%3A+A+comprehensive+benchmark+for+continual+learning+in+large+lang)
264. Xin Wang, Yudong Chen, and Wenwu Zhu. A survey on curriculum learning. IEEE transactions on pattern analysis and machine intelligence, 44(9):4555–4576, 2021. [find](https://scholar.google.com/scholar?q=Xin+Wang%2C+Yudong+Chen%2C+and+Wenwu+Zhu%2E+A+survey+on+curriculum+learning%2E+IEEE+transactions+on+pattern+analysis+and+machine+intelligence%2C+44%289%29%3A4555%E2%80%934576%2C+2021%2E)
265. Xinyuan Wang, Chenxi Li, Zhen Wang, Fan Bai, Haotian Luo, Jiayou Zhang, Nebojsa Jojic, Eric P Xing, and Zhiting Hu. [Promptagent: Strategic planning with language models enables expert-level prompt optimization](https://md.research.elamur.ai/free/en/papers/wang-2023-promptagent-strategic-planning-language-models/). arXiv preprint arXiv:2310.16427, 2023d.
266. Yinjie Wang, Ling Yang, Guohao Li, Mengdi Wang, and Bryon Aragam. Scoreflow: Mastering LLM agent workflows via score-based preference optimization. arXiv preprint arXiv:2502.04306, 2025n. — [arXiv:2502.04306](https://arxiv.org/abs/2502.04306) [find](https://scholar.google.com/scholar?q=Yinjie+Wang%2C+Ling+Yang%2C+Guohao+Li%2C+Mengdi+Wang%2C+and+Bryon+Aragam%2E+Scoreflow%3A+Mastering+LLM+agent+workflows+via+score%2Dbased+preference+optimization%2E+arXiv+preprint+arXiv%3A2502%2E04306%2C+2025n%2E+%E2%80%94+%5BarXiv%3A250)
267. Yizhong Wang, Yeganeh Kordi, Swaroop Mishra, Alisa Liu, Noah A Smith, Daniel Khashabi, and Hannaneh Hajishirzi. Self-instruct: Aligning language models with self-generated instructions. arXiv preprint arXiv:2212.10560, 2022. [find](https://scholar.google.com/scholar?q=Yizhong+Wang%2C+Yeganeh+Kordi%2C+Swaroop+Mishra%2C+Alisa+Liu%2C+Noah+A+Smith%2C+Daniel+Khashabi%2C+and+Hannaneh+Hajishirzi%2E+Self%2Dinstruct%3A+Aligning+language+models+with+self%2Dgenerated+instructions%2E+arXiv+preprint)
268. Yue Wang, Tianfan Fu, Yinlong Xu, Zihan Ma, Hongxia Xu, Bang Du, Yingzhou Lu, Honghao Gao, Jian Wu, and Jintai Chen. Twin-gpt: digital twins for clinical trials via large language model. ACM Transactions on Multimedia Computing, Communications and Applications, 2024h. [find](https://scholar.google.com/scholar?q=Yue+Wang%2C+Tianfan+Fu%2C+Yinlong+Xu%2C+Zihan+Ma%2C+Hongxia+Xu%2C+Bang+Du%2C+Yingzhou+Lu%2C+Honghao+Gao%2C+Jian+Wu%2C+and+Jintai+Chen%2E+Twin%2Dgpt%3A+digital+twins+for+clinical+trials+via+large+language+model%2E+ACM+Transacti)
269. Zhenhailong Wang, Haiyang Xu, Junyang Wang, Xi Zhang, Ming Yan, Ji Zhang, Fei Huang, and Heng Ji. Mobile-agent-e: Self-evolving mobile assistant for complex tasks. arXiv preprint arXiv:2501.11733, 2025o. — [arXiv:2501.11733](https://arxiv.org/abs/2501.11733) [find](https://scholar.google.com/scholar?q=Zhenhailong+Wang%2C+Haiyang+Xu%2C+Junyang+Wang%2C+Xi+Zhang%2C+Ming+Yan%2C+Ji+Zhang%2C+Fei+Huang%2C+and+Heng+Ji%2E+Mobile%2Dagent%2De%3A+Self%2Devolving+mobile+assistant+for+complex+tasks%2E+arXiv+preprint+arXiv%3A2501%2E11733%2C+202)
270. Zhenting Wang, Guofeng Cui, Kun Wan, and Wentian Zhao. Dump: Automated distribution-level curriculum learning for rl-based llm post-training. arXiv preprint arXiv:2504.09710, 2025p. — [arXiv:2504.09710](https://arxiv.org/abs/2504.09710) [find](https://scholar.google.com/scholar?q=Zhenting+Wang%2C+Guofeng+Cui%2C+Kun+Wan%2C+and+Wentian+Zhao%2E+Dump%3A+Automated+distribution%2Dlevel+curriculum+learning+for+rl%2Dbased+llm+post%2Dtraining%2E+arXiv+preprint+arXiv%3A2504%2E09710%2C+2025p%2E+%E2%80%94+%5BarXiv%3A2504%2E0971)
271. Zihan Wang, Kangrui Wang, Qineng Wang, Pingyue Zhang, Linjie Li, Zhengyuan Yang, Xing Jin, Kefan Yu, Minh Nhat Nguyen, Licheng Liu, Eli Gottlieb, Yiping Lu, Kyunghyun Cho, Jiajun Wu, Li Fei-Fei, Lijuan Wang, Yejin Choi, and Manling Li. Ragen: Understanding self-evolution in llm agents via multi-turn… — [RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/wang-2025-ragen-understanding-self-evolution-llm/)
272. Ziqi Wang, Le Hou, Tianjian Lu, Yuexin Wu, Yunxuan Li, Hongkun Yu, and Heng Ji. Enabling lanuguage models to implicitly learn self-improvement. In The Twelfth International Conference on Learning Representations, 2024i. URL [https://openreview.net/forum?id=2tVHNRZuCs](https://openreview.net/forum?id=2tVHNRZuCs). [↗](https://openreview.net/forum?id=2tVHNRZuCs)
273. Zora Zhiruo Wang, Jiayuan Mao, Daniel Fried, and Graham Neubig. [Agent workflow memory](https://md.research.elamur.ai/free/en/papers/wang-2024-agent-workflow-memory/). arXiv preprint arXiv:2409.07429, 2024j.
274. Boyi Wei, Benedikt Stroebl, Jiacen Xu, Joie Zhang, Zhou Li, and Peter Henderson. Dynamic risk assessments for offensive cybersecurity agents. arXiv preprint arXiv:2505.18384, 2025a. [find](https://scholar.google.com/scholar?q=Boyi+Wei%2C+Benedikt+Stroebl%2C+Jiacen+Xu%2C+Joie+Zhang%2C+Zhou+Li%2C+and+Peter+Henderson%2E+Dynamic+risk+assessments+for+offensive+cybersecurity+agents%2E+arXiv+preprint+arXiv%3A2505%2E18384%2C+2025a%2E)
275. Jason Wei, Zhiqing Sun, Spencer Papay, Scott McKinney, Jeffrey Han, Isa Fulford, Hyung Won Chung, Alex Tachard Passos, William Fedus, and Amelia Glaese. [Browsecomp: A simple yet challenging benchmark for browsing agents](https://md.research.elamur.ai/free/en/papers/wei-2025-browsecomp-simple-yet-challenging-benchmark/). arXiv preprint arXiv:2504.12516, 2025b.
276. Lai Wei, Yuting Li, Chen Wang, Yue Wang, Linghe Kong, Weiran Huang, and Lichao Sun. Unsupervised post-training for multi-modal llm reasoning via grpo, 2025c. URL https://arxiv.org/abs/2505.22453. — [arXiv:2505.22453](https://arxiv.org/abs/2505.22453) [↗](https://arxiv.org/abs/2505.22453)
277. Qianshan Wei, Tengchao Yang, Yaochen Wang, Xinfeng Li, Lijun Li, Zhenfei Yin, Yi Zhan, Thorsten Holz, Zhiqiang Lin, and XiaoFeng Wang. A-memguard: A proactive defense framework for llm-based agent memory. arXiv preprint arXiv:2510.02373, 2025d. — [arXiv:2510.02373](https://arxiv.org/abs/2510.02373) [find](https://scholar.google.com/scholar?q=Qianshan+Wei%2C+Tengchao+Yang%2C+Yaochen+Wang%2C+Xinfeng+Li%2C+Lijun+Li%2C+Zhenfei+Yin%2C+Yi+Zhan%2C+Thorsten+Holz%2C+Zhiqiang+Lin%2C+and+XiaoFeng+Wang%2E+A%2Dmemguard%3A+A+proactive+defense+framework+for+llm%2Dbased+agent+mem)
278. Colin White, Samuel Dooley, Manley Roberts, Arka Pal, Ben Feuer, Siddhartha Jain, Ravid Shwartz-Ziv, Neel Jain, Khalid Saifullah, Sreemanti Dey, et al. Livebench: A challenging, contamination-limited llm benchmark. arXiv preprint arXiv:2406.19314, 2024. [find](https://scholar.google.com/scholar?q=Colin+White%2C+Samuel+Dooley%2C+Manley+Roberts%2C+Arka+Pal%2C+Ben+Feuer%2C+Siddhartha+Jain%2C+Ravid+Shwartz%2DZiv%2C+Neel+Jain%2C+Khalid+Saifullah%2C+Sreemanti+Dey%2C+et+al%2E+Livebench%3A+A+challenging%2C+contamination%2Dlimited+)
279. Noam Wies, Yoav Levine, and Amnon Shashua. [The learnability of in-context learning](https://md.research.elamur.ai/free/en/papers/wies-2023-learnability-context-learning/). Advances in Neural Information Processing Systems, 36:36637–36651, 2023.
280. Jialong Wu, Wenbiao Yin, Yong Jiang, Zhenglin Wang, Zekun Xi, Runnan Fang, Linhai Zhang, Yulan He, Deyu Zhou, Pengjun Xie, et al. [Webwalker: Benchmarking llms in web traversal](https://md.research.elamur.ai/free/en/papers/wu-2025-webwalker-benchmarking-llms-web-traversal/). arXiv preprint arXiv:2501.07572, 2025.
281. Mengsong Wu, Tong Zhu, Han Han, Chuanyuan Tan, Xiang Zhang, and Wenliang Chen. Seal-tools: Self-instruct tool learning dataset for agent tuning and detailed benchmark. In CCF International Conference on Natural Language Processing and Chinese Computing, pp. 372–384. Springer, 2024. [find](https://scholar.google.com/scholar?q=Mengsong+Wu%2C+Tong+Zhu%2C+Han+Han%2C+Chuanyuan+Tan%2C+Xiang+Zhang%2C+and+Wenliang+Chen%2E+Seal%2Dtools%3A+Self%2Dinstruct+tool+learning+dataset+for+agent+tuning+and+detailed+benchmark%2E+In+CCF+International+Conference+)
282. Zhiheng Xi, Dingwen Yang, Jixuan Huang, Jiafu Tang, Guanyu Li, Yiwen Ding, Wei He, Boyang Hong, Shihan Do, Wenyu Zhan, et al. Enhancing llm reasoning via critique models with test-time and training-time supervision. arXiv preprint arXiv:2411.16579, 2024. — [arXiv:2411.16579](https://arxiv.org/abs/2411.16579) [find](https://scholar.google.com/scholar?q=Zhiheng+Xi%2C+Dingwen+Yang%2C+Jixuan+Huang%2C+Jiafu+Tang%2C+Guanyu+Li%2C+Yiwen+Ding%2C+Wei+He%2C+Boyang+Hong%2C+Shihan+Do%2C+Wenyu+Zhan%2C+et+al%2E+Enhancing+llm+reasoning+via+critique+models+with+test%2Dtime+and+training%2Dti)
283. Chunqiu Steven Xia, Zhe Wang, Yan Yang, Yuxiang Wei, and Lingming Zhang. Live-swe-agent: Can software engineering agents self-evolve on the fly? arXiv preprint arXiv:2511.13646, 2025a. — [arXiv:2511.13646](https://arxiv.org/abs/2511.13646) [find](https://scholar.google.com/scholar?q=Chunqiu+Steven+Xia%2C+Zhe+Wang%2C+Yan+Yang%2C+Yuxiang+Wei%2C+and+Lingming+Zhang%2E+Live%2Dswe%2Dagent%3A+Can+software+engineering+agents+self%2Devolve+on+the+fly%3F+arXiv+preprint+arXiv%3A2511%2E13646%2C+2025a%2E+%E2%80%94+%5BarXiv%3A2511%2E1)
284. Peng Xia, Kaide Zeng, Jiaqi Liu, Can Qin, Fang Wu, Yiyang Zhou, Caiming Xiong, and Huaxiu Yao. Agent0: Unleashing self-evolving agents from zero data via tool-integrated reasoning. arXiv preprint arXiv:2511.16043, 2025b. — [arXiv:2511.16043](https://arxiv.org/abs/2511.16043) [find](https://scholar.google.com/scholar?q=Peng+Xia%2C+Kaide+Zeng%2C+Jiaqi+Liu%2C+Can+Qin%2C+Fang+Wu%2C+Yiyang+Zhou%2C+Caiming+Xiong%2C+and+Huaxiu+Yao%2E+Agent0%3A+Unleashing+self%2Devolving+agents+from+zero+data+via+tool%2Dintegrated+reasoning%2E+arXiv+preprint+arXi)
285. Jinyu Xiang, Jiayi Zhang, Zhaoyang Yu, Fengwei Teng, Jinhao Tu, Xinbing Liang, Sirui Hong, Chenglin Wu, and Yuyu Luo. Self-supervised prompt optimization. arXiv preprint arXiv:2502.06855, 2025. [find](https://scholar.google.com/scholar?q=Jinyu+Xiang%2C+Jiayi+Zhang%2C+Zhaoyang+Yu%2C+Fengwei+Teng%2C+Jinhao+Tu%2C+Xinbing+Liang%2C+Sirui+Hong%2C+Chenglin+Wu%2C+and+Yuyu+Luo%2E+Self%2Dsupervised+prompt+optimization%2E+arXiv+preprint+arXiv%3A2502%2E06855%2C+2025%2E)
286. Han Xiao, Guozhi Wang, Yuxiang Chai, Zimu Lu, Weifeng Lin, Hao He, Lue Fan, Liuyang Bian, Rui Hu, Liang Liu, et al. Ui-genie: A self-improving approach for iteratively boosting mllm-based mobile gui agents. arXiv preprint arXiv:2505.21496, 2025a. — [arXiv:2505.21496](https://arxiv.org/abs/2505.21496) [find](https://scholar.google.com/scholar?q=Han+Xiao%2C+Guozhi+Wang%2C+Yuxiang+Chai%2C+Zimu+Lu%2C+Weifeng+Lin%2C+Hao+He%2C+Lue+Fan%2C+Liuyang+Bian%2C+Rui+Hu%2C+Liang+Liu%2C+et+al%2E+Ui%2Dgenie%3A+A+self%2Dimproving+approach+for+iteratively+boosting+mllm%2Dbased+mobile+gui+a)
287. Yijia Xiao, Edward Sun, Di Luo, and Wei Wang. Tradingagents: Multi-agents llm financial trading framework. arXiv preprint arXiv:2412.20138, 2024. — [arXiv:2412.20138](https://arxiv.org/abs/2412.20138) [find](https://scholar.google.com/scholar?q=Yijia+Xiao%2C+Edward+Sun%2C+Di+Luo%2C+and+Wei+Wang%2E+Tradingagents%3A+Multi%2Dagents+llm+financial+trading+framework%2E+arXiv+preprint+arXiv%3A2412%2E20138%2C+2024%2E+%E2%80%94+%5BarXiv%3A2412%2E20138%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2412%2E20138%29)
288. Yunzhong Xiao, Yangmin Li, Hewei Wang, Yunlong Tang, and Zora Zhiruo Wang. Toolmem: Enhancing multimodal agents with learnable tool capability memory. arXiv preprint arXiv:2510.06664, 2025b. — [arXiv:2510.06664](https://arxiv.org/abs/2510.06664) [find](https://scholar.google.com/scholar?q=Yunzhong+Xiao%2C+Yangmin+Li%2C+Hewei+Wang%2C+Yunlong+Tang%2C+and+Zora+Zhiruo+Wang%2E+Toolmem%3A+Enhancing+multimodal+agents+with+learnable+tool+capability+memory%2E+arXiv+preprint+arXiv%3A2510%2E06664%2C+2025b%2E+%E2%80%94+%5BarXiv%3A)
289. Tianbao Xie, Danyang Zhang, Jixuan Chen, Xiaochuan Li, Siheng Zhao, Ruisheng Cao, Toh J Hua, Zhoujun Cheng, Dongchan Shin, Fangyu Lei, et al. [Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments](https://md.research.elamur.ai/free/en/papers/xie-2024-osworld-benchmarking-multimodal-agents-open/). Advances in Neural Information Processing Systems, 37:52040– 52094…
290. Wenpeng Xing, Zhonghao Qi, Yupeng Qin, Yilin Li, Caini Chang, Jiahui Yu, Changting Lin, Zhenzhen Xie, and Meng Han. Mcp-guard: A defense framework for model context protocol integrity in large language model applications. arXiv preprint arXiv:2508.10991, 2025. — [arXiv:2508.10991](https://arxiv.org/abs/2508.10991) [find](https://scholar.google.com/scholar?q=Wenpeng+Xing%2C+Zhonghao+Qi%2C+Yupeng+Qin%2C+Yilin+Li%2C+Caini+Chang%2C+Jiahui+Yu%2C+Changting+Lin%2C+Zhenzhen+Xie%2C+and+Meng+Han%2E+Mcp%2Dguard%3A+A+defense+framework+for+model+context+protocol+integrity+in+large+languag)
291. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. [Wizardlm: Empowering large pre-trained language models to follow complex instructions](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/). In The Twelfth International Conference on Learning Representations, 2024a.
292. Frank F Xu, Yufan Song, Boxuan Li, Yuxuan Tang, Kritanjali Jain, Mengxue Bao, Zora Z Wang, Xuhui Zhou, Zhitong Guo, Murong Cao, et al. [Theagentcompany: benchmarking llm agents on consequential real world tasks](https://md.research.elamur.ai/free/en/papers/xu-2024-theagentcompany-benchmarking-llm-agents/). arXiv preprint arXiv:2412.14161, 2024b.
293. Wujiang Xu, Kai Mei, Hang Gao, Juntao Tan, Zujie Liang, and Yongfeng Zhang. [A-mem: Agentic memory for llm agents](https://md.research.elamur.ai/free/en/papers/xu-2025-mem-agentic-memory-llm-agents/). arXiv preprint arXiv:2502.12110, 2025a.
294. Zicheng Xu, Guanchu Wang, Guangyao Zheng, Yu-Neng Chuang, Alexander Szalay, Xia Hu, and Vladimir Braverman. Self-ensemble: Mitigating confidence distortion for large language models, 2025b. URL https://arxiv.org/abs/2506.01951. [↗](https://arxiv.org/abs/2506.01951)
295. Cilin Yan, Jingyun Wang, Lin Zhang, Ruihui Zhao, Xiaopu Wu, Kai Xiong, Qingsong Liu, Guoliang Kang, and Yangyang Kang. Efficient and accurate prompt optimization: the benefit of memory in exemplar-guided reflection. arXiv preprint arXiv:2411.07446, 2024. [find](https://scholar.google.com/scholar?q=Cilin+Yan%2C+Jingyun+Wang%2C+Lin+Zhang%2C+Ruihui+Zhao%2C+Xiaopu+Wu%2C+Kai+Xiong%2C+Qingsong+Liu%2C+Guoliang+Kang%2C+and+Yangyang+Kang%2E+Efficient+and+accurate+prompt+optimization%3A+the+benefit+of+memory+in+exemplar%2Dgui)
296. Sikuan Yan, Xiufeng Yang, Zuchao Huang, Ercong Nie, Zifeng Ding, Zonggen Li, Xiaowen Ma, Kristian Kersting, Jeff Z. Pan, Hinrich Schütze, Volker Tresp, and Yunpu Ma. [Memory-r1: Enhancing large language model agents to manage and utilize memories via reinforcement learning](https://md.research.elamur.ai/free/en/papers/yan-2026-memory-r1-enhancing-large-language/). arXiv preprint arXiv:2508.…
297. Cheng Yang, Xuemeng Yang, Licheng Wen, Daocheng Fu, Jianbiao Mei, Rong Wu, Pinlong Cai, Yufan Shen, Nianchen Deng, Botian Shi, Yu Qiao, and Haifeng Li. Learning on the job: An experience-driven self-evolving agent for long-horizon tasks. arXiv preprint arXiv:2510.08002, 2025a. — [arXiv:2510.08002](https://arxiv.org/abs/2510.08002) [find](https://scholar.google.com/scholar?q=Cheng+Yang%2C+Xuemeng+Yang%2C+Licheng+Wen%2C+Daocheng+Fu%2C+Jianbiao+Mei%2C+Rong+Wu%2C+Pinlong+Cai%2C+Yufan+Shen%2C+Nianchen+Deng%2C+Botian+Shi%2C+Yu+Qiao%2C+and+Haifeng+Li%2E+Learning+on+the+job%3A+An+experience%2Ddriven+self%2De)
298. Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V Le, Denny Zhou, and Xinyun Chen. [Large language models as optimizers](https://md.research.elamur.ai/free/en/papers/yang-2023-large-language-models-optimizers/). arXiv preprint arXiv:2309.03409, 2023.
299. John Yang, Carlos E Jimenez, Alex L Zhang, Kilian Lieret, Joyce Yang, Xindi Wu, Ori Press, Niklas Muennighoff, Gabriel Synnaeve, Karthik R Narasimhan, et al. Swe-bench multimodal: Do ai systems generalize to visual software domains? arXiv preprint arXiv:2410.03859, 2024. [find](https://scholar.google.com/scholar?q=John+Yang%2C+Carlos+E+Jimenez%2C+Alex+L+Zhang%2C+Kilian+Lieret%2C+Joyce+Yang%2C+Xindi+Wu%2C+Ori+Press%2C+Niklas+Muennighoff%2C+Gabriel+Synnaeve%2C+Karthik+R+Narasimhan%2C+et+al%2E+Swe%2Dbench+multimodal%3A+Do+ai+systems+genera)
300. Kaiqi Yang, Hang Li, Yucheng Chu, Ahreum Han, Yasemin Copur-Gencturk, Jiliang Tang, and Hui Liu. A llm-driven multi-agent systems for professional development of mathematics teachers. arXiv preprint arXiv:2507.05292, 2025b. URL https://arxiv.org/abs/2507.05292. — [arXiv:2507.05292](https://arxiv.org/abs/2507.05292) [↗](https://arxiv.org/abs/2507.05292)
301. Yue Yang, MingKang Chen, Qihua Liu, Mengkang Hu, Qiguang Chen, Gengrui Zhang, Shuyue Hu, Guangtao Zhai, Yu Qiao, Yu Wang, et al. Truly assessing fluid intelligence of large language models through dynamic reasoning evaluation. arXiv preprint arXiv:2506.02648, 2025c. — [arXiv:2506.02648](https://arxiv.org/abs/2506.02648) [find](https://scholar.google.com/scholar?q=Yue+Yang%2C+MingKang+Chen%2C+Qihua+Liu%2C+Mengkang+Hu%2C+Qiguang+Chen%2C+Gengrui+Zhang%2C+Shuyue+Hu%2C+Guangtao+Zhai%2C+Yu+Qiao%2C+Yu+Wang%2C+et+al%2E+Truly+assessing+fluid+intelligence+of+large+language+models+through+dyn)
302. Yutao Yang, Jie Zhou, Xuanwen Ding, Tianyu Huai, Shunyu Liu, Qin Chen, Yuan Xie, and Liang He. Recent advances of foundation language models-based continual learning: A survey. ACM Computing Surveys, 57(5):1–38, 2025d. [find](https://scholar.google.com/scholar?q=Yutao+Yang%2C+Jie+Zhou%2C+Xuanwen+Ding%2C+Tianyu+Huai%2C+Shunyu+Liu%2C+Qin+Chen%2C+Yuan+Xie%2C+and+Liang+He%2E+Recent+advances+of+foundation+language+models%2Dbased+continual+learning%3A+A+survey%2E+ACM+Computing+Surveys%2C+)
303. Ziyi Yang, Weizhou Shen, Chenliang Li, Ruijun Chen, Fanqi Wan, Ming Yan, Xiaojun Quan, and Fei Huang. Spell: Self-play reinforcement learning for evolving long-context language models. arXiv preprint arXiv:2509.23863, 2025e. — [arXiv:2509.23863](https://arxiv.org/abs/2509.23863) [find](https://scholar.google.com/scholar?q=Ziyi+Yang%2C+Weizhou+Shen%2C+Chenliang+Li%2C+Ruijun+Chen%2C+Fanqi+Wan%2C+Ming+Yan%2C+Xiaojun+Quan%2C+and+Fei+Huang%2E+Spell%3A+Self%2Dplay+reinforcement+learning+for+evolving+long%2Dcontext+language+models%2E+arXiv+preprint+)
304. Shunyu Yao, Howard Chen, John Yang, and Karthik Narasimhan. [Webshop: Towards scalable real-world web interaction with grounded language agents](https://md.research.elamur.ai/free/en/papers/yao-2022-webshop-towards-scalable-real-world/). Advances in Neural Information Processing Systems, 35: 20744–20757, 2022.
305. Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan. tau-bench: A benchmark for tool-agent-user interaction in real-world domains. arXiv preprint arXiv:2406.[12045, 2024](https://md.research.elamur.ai/free/en/papers/yao-2024-tau-bench-benchmark-tool/).
306. Rui Ye, Xiangru Liu, Qingyun Wu, Xinyuan Pang, Zhaopeng Yin, Lu Bai, et al. X-mas: Towards building multi-agent systems with heterogeneous llms. arXiv preprint arXiv:2505.16997, 2025a. — [arXiv:2505.16997](https://arxiv.org/abs/2505.16997) [find](https://scholar.google.com/scholar?q=Rui+Ye%2C+Xiangru+Liu%2C+Qingyun+Wu%2C+Xinyuan+Pang%2C+Zhaopeng+Yin%2C+Lu+Bai%2C+et+al%2E+X%2Dmas%3A+Towards+building+multi%2Dagent+systems+with+heterogeneous+llms%2E+arXiv+preprint+arXiv%3A2505%2E16997%2C+2025a%2E+%E2%80%94+%5BarXiv%3A2505%2E1)
307. Rui Ye et al. Mas-gpt: Training llms to build llm-based multi-agent systems. arXiv preprint, 2025b. [find](https://scholar.google.com/scholar?q=Rui+Ye+et+al%2E+Mas%2Dgpt%3A+Training+llms+to+build+llm%2Dbased+multi%2Dagent+systems%2E+arXiv+preprint%2C+2025b%2E)
308. S. Yellamraju, , et al. [TextGrad: Automatic "differentiation" via text](https://md.research.elamur.ai/free/en/papers/yuksekgonul-2024-textgrad-automatic-differentiation-text/). arXiv preprint arXiv:2406.07496, 2024.
309. Li Yin and Zhangyang Wang. Llm-autodiff: Auto-differentiate any llm workflow. arXiv e-prints, pp. arXiv– 2501, 2025. [find](https://scholar.google.com/scholar?q=Li+Yin+and+Zhangyang+Wang%2E+Llm%2Dautodiff%3A+Auto%2Ddifferentiate+any+llm+workflow%2E+arXiv+e%2Dprints%2C+pp%2E+arXiv%E2%80%93+2501%2C+2025%2E)
310. Xunjian Yin, Xinyi Wang, Liangming Pan, Li Lin, Xiaojun Wan, and William Yang Wang. Gödel agent: A self-referential agent framework for recursive self-improvement, 2025. URL https://arxiv.org/abs/ 2410.04444. [↗](https://arxiv.org/abs/)
311. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Weinan Dai, Tiantian Fan, Gaohong Liu, Lingjun Liu, et al. [Dapo: An open-source llm reinforcement learning system at scale](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/). arXiv preprint arXiv:2503.14476, 2025a.
312. Wenhao Yu, Zhenwen Liang, Chengsong Huang, Kishan Panaganti, Tianqing Fang, Haitao Mi, and Dong Yu. Guided self-evolving llms with minimal human supervision. arXiv preprint arXiv:2512.02472, 2025b. — [arXiv:2512.02472](https://arxiv.org/abs/2512.02472) [find](https://scholar.google.com/scholar?q=Wenhao+Yu%2C+Zhenwen+Liang%2C+Chengsong+Huang%2C+Kishan+Panaganti%2C+Tianqing+Fang%2C+Haitao+Mi%2C+and+Dong+Yu%2E+Guided+self%2Devolving+llms+with+minimal+human+supervision%2E+arXiv+preprint+arXiv%3A2512%2E02472%2C+2025b%2E+%E2%80%94+)
313. Lifan Yuan, Yangyi Chen, Xingyao Wang, Yi Fung, Hao Peng, and Heng Ji. CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets. In 12th International Conference on Learning Representations, 2024a. URL [https://openreview.net/forum?id=G0vdDSt9XM](https://openreview.net/forum?id=G0vdDSt9XM). [↗](https://openreview.net/forum?id=G0vdDSt9XM)
314. Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, and Deqing Yang. Evoagent: Towards automatic multi-agent generation via evolutionary algorithms. arXiv preprint arXiv:2406.14228, 2024b. [find](https://scholar.google.com/scholar?q=Siyu+Yuan%2C+Kaitao+Song%2C+Jiangjie+Chen%2C+Xu+Tan%2C+Dongsheng+Li%2C+and+Deqing+Yang%2E+Evoagent%3A+Towards+automatic+multi%2Dagent+generation+via+evolutionary+algorithms%2E+arXiv+preprint+arXiv%3A2406%2E14228%2C+2024b%2E)
315. Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, and Deqing Yang. Evoagent: Towards automatic multi-agent generation via evolutionary algorithms, 2025a. URL https://arxiv.org/abs/ 2406.14228. [↗](https://arxiv.org/abs/)
316. Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, and Jason Weston. Self-rewarding language models. arXiv preprint arXiv:2401.10020, 2024c. [find](https://scholar.google.com/scholar?q=Weizhe+Yuan%2C+Richard+Yuanzhe+Pang%2C+Kyunghyun+Cho%2C+Xian+Li%2C+Sainbayar+Sukhbaatar%2C+Jing+Xu%2C+and+Jason+Weston%2E+Self%2Drewarding+language+models%2E+arXiv+preprint+arXiv%3A2401%2E10020%2C+2024c%2E)
317. Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, and Jason E. Weston. Self-rewarding language models. In Proceedings of the 41st International Conference on Machine Learning, volume 235 of Proceedings of Machine Learning Research, pp. 57905–57923. PMLR, 2024d… [find](https://scholar.google.com/scholar?q=Weizhe+Yuan%2C+Richard+Yuanzhe+Pang%2C+Kyunghyun+Cho%2C+Xian+Li%2C+Sainbayar+Sukhbaatar%2C+Jing+Xu%2C+and+Jason+E%2E+Weston%2E+Self%2Drewarding+language+models%2E+In+Proceedings+of+the+41st+International+Conference+on+Ma)
318. Weizhe Yuan, Richard Yuanzhe Pang, Kyunghyun Cho, Xian Li, Sainbayar Sukhbaatar, Jing Xu, and Jason Weston. Self-rewarding language models, 2025b. URL https://arxiv.org/abs/2401.10020. [↗](https://arxiv.org/abs/2401.10020)
319. Xinbin Yuan, Jian Zhang, Kaixin Li, Zhuoxuan Cai, Lujian Yao, Jie Chen, Enguang Wang, Qibin Hou, Jinwei Chen, Peng-Tao Jiang, and Bo Li. Enhancing visual grounding for gui agents via self-evolutionary reinforcement learning. arXiv preprint arXiv:2505.12370, 2025c. — [arXiv:2505.12370](https://arxiv.org/abs/2505.12370) [find](https://scholar.google.com/scholar?q=Xinbin+Yuan%2C+Jian+Zhang%2C+Kaixin+Li%2C+Zhuoxuan+Cai%2C+Lujian+Yao%2C+Jie+Chen%2C+Enguang+Wang%2C+Qibin+Hou%2C+Jinwei+Chen%2C+Peng%2DTao+Jiang%2C+and+Bo+Li%2E+Enhancing+visual+grounding+for+gui+agents+via+self%2Devolutionary)
320. Zheng Yuan, Hongyi Yuan, Chuanqi Tan, Wei Wang, Songfang Huang, and Fei Huang. [Rrhf: Rank responses to align language models with human feedback without tears](https://md.research.elamur.ai/free/en/papers/yuan-2023-rrhf-rank-responses-align-language/). arXiv preprint arXiv:2304.05302, 2023.
321. Murong Yue, Wenhan Lyu, Wijdane Mifdal, Jennifer Suh, Yixuan Zhang, and Ziyu Yao. Mathvc: An llm-simulated multi-character virtual classroom for mathematics education. arXiv preprint arXiv:2404.06711, 2025. URL https://arxiv.org/abs/2404.06711. — [arXiv:2404.06711](https://arxiv.org/abs/2404.06711) [↗](https://arxiv.org/abs/2404.06711)
322. Eric Zelikman, Yuhuai Wu, Jesse Mu, and Noah Goodman. [Star: Bootstrapping reasoning with reasoning](https://md.research.elamur.ai/free/en/papers/zelikman-2022-star-bootstrapping-reasoning-reasoning/). Advances in Neural Information Processing Systems, 35:15476–15488, 2022.
323. Eric Zelikman, Georges Harik, Yijia Shao, Varuna Jayasiri, Nick Haber, and Noah D Goodman. [Quiet-star: Language models can teach themselves to think before speaking](https://md.research.elamur.ai/free/en/papers/al-2024-quiet-star-language-models-teach/). arXiv preprint arXiv:2403.09629, 2024.
324. Yunpeng Zhai, Shuchang Tao, Cheng Chen, Anni Zou, Ziqian Chen, Qingxu Fu, Shinji Mai, Li Yu, Jiaji Deng, Zouying Cao, Zhaoyang Liu, Bolin Ding, and Jingren Zhou. Agentevolver: Towards efficient self-evolving agent system. arXiv preprint arXiv:2511.10395, 2025. — [arXiv:2511.10395](https://arxiv.org/abs/2511.10395) [find](https://scholar.google.com/scholar?q=Yunpeng+Zhai%2C+Shuchang+Tao%2C+Cheng+Chen%2C+Anni+Zou%2C+Ziqian+Chen%2C+Qingxu+Fu%2C+Shinji+Mai%2C+Li+Yu%2C+Jiaji+Deng%2C+Zouying+Cao%2C+Zhaoyang+Liu%2C+Bolin+Ding%2C+and+Jingren+Zhou%2E+Agentevolver%3A+Towards+efficient+self%2De)
325. Danyang Zhang, Lu Chen, Situo Zhang, Hongshen Xu, Zihan Zhao, and Kai Yu. Large language models are semi-parametric reinforcement learning agents. Advances in Neural Information Processing Systems, 36, 2024a. [find](https://scholar.google.com/scholar?q=Danyang+Zhang%2C+Lu+Chen%2C+Situo+Zhang%2C+Hongshen+Xu%2C+Zihan+Zhao%2C+and+Kai+Yu%2E+Large+language+models+are+semi%2Dparametric+reinforcement+learning+agents%2E+Advances+in+Neural+Information+Processing+Systems%2C+36)
326. Enci Zhang, Xingang Yan, Wei Lin, Tianxiang Zhang, and Qianchun Lu. Learning like humans: Advancing llm reasoning capabilities via adaptive difficulty curriculum learning and expert-guided self-reformulation. arXiv preprint arXiv:2505.08364, 2025a. [find](https://scholar.google.com/scholar?q=Enci+Zhang%2C+Xingang+Yan%2C+Wei+Lin%2C+Tianxiang+Zhang%2C+and+Qianchun+Lu%2E+Learning+like+humans%3A+Advancing+llm+reasoning+capabilities+via+adaptive+difficulty+curriculum+learning+and+expert%2Dguided+self%2Dreform)
327. Genghan Zhang, Weixin Liang, Olivia Hsu, and Kunle Olukotun. Adaptive self-improvement llm agentic system for ml library development. arXiv preprint arXiv:2502.02534, 2025b. — [arXiv:2502.02534](https://arxiv.org/abs/2502.02534) [find](https://scholar.google.com/scholar?q=Genghan+Zhang%2C+Weixin+Liang%2C+Olivia+Hsu%2C+and+Kunle+Olukotun%2E+Adaptive+self%2Dimprovement+llm+agentic+system+for+ml+library+development%2E+arXiv+preprint+arXiv%3A2502%2E02534%2C+2025b%2E+%E2%80%94+%5BarXiv%3A2502%2E02534%5D%28https)
328. Guanghui Zhang, Kang Chen, Guohao Wan, Hao Chang, Hao Cheng, et al. Evoflow: Evolving diverse agentic workflows on the fly. arXiv preprint arXiv:2502.07373, 2025c. — [arXiv:2502.07373](https://arxiv.org/abs/2502.07373) [find](https://scholar.google.com/scholar?q=Guanghui+Zhang%2C+Kang+Chen%2C+Guohao+Wan%2C+Hao+Chang%2C+Hao+Cheng%2C+et+al%2E+Evoflow%3A+Evolving+diverse+agentic+workflows+on+the+fly%2E+arXiv+preprint+arXiv%3A2502%2E07373%2C+2025c%2E+%E2%80%94+%5BarXiv%3A2502%2E07373%5D%28https%3A%2F%2Farxiv%2Eo)
329. Guanghui Zhang, Li Niu, Jianwei Fang, Kun Wang, Lu Bai, et al. Multi-agent architecture search via agentic supernet. arXiv preprint arXiv:2502.04180, 2025d. — [arXiv:2502.04180](https://arxiv.org/abs/2502.04180) [find](https://scholar.google.com/scholar?q=Guanghui+Zhang%2C+Li+Niu%2C+Jianwei+Fang%2C+Kun+Wang%2C+Lu+Bai%2C+et+al%2E+Multi%2Dagent+architecture+search+via+agentic+supernet%2E+arXiv+preprint+arXiv%3A2502%2E04180%2C+2025d%2E+%E2%80%94+%5BarXiv%3A2502%2E04180%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F)
330. Guibin Zhang, Muxin Fu, Guancheng Wan, Miao Yu, Kun Wang, and Shuicheng Yan. G-memory: Tracing hierarchical memory for multi-agent systems. arXiv preprint arXiv:2506.07398, 2025e. — [arXiv:2506.07398](https://arxiv.org/abs/2506.07398) [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Muxin+Fu%2C+Guancheng+Wan%2C+Miao+Yu%2C+Kun+Wang%2C+and+Shuicheng+Yan%2E+G%2Dmemory%3A+Tracing+hierarchical+memory+for+multi%2Dagent+systems%2E+arXiv+preprint+arXiv%3A2506%2E07398%2C+2025e%2E+%E2%80%94+%5BarXiv%3A2506%2E07398%5D)
331. Guibin Zhang, Muxin Fu, and Shuicheng Yan. Memgen: Weaving generative latent memory for self-evolving agents. arXiv preprint arXiv:2509.24704, 2025f. — [arXiv:2509.24704](https://arxiv.org/abs/2509.24704) [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Muxin+Fu%2C+and+Shuicheng+Yan%2E+Memgen%3A+Weaving+generative+latent+memory+for+self%2Devolving+agents%2E+arXiv+preprint+arXiv%3A2509%2E24704%2C+2025f%2E+%E2%80%94+%5BarXiv%3A2509%2E24704%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2509%2E24)
332. Guibin Zhang, Haotian Ren, Chong Zhan, Zhenhong Zhou, Junhao Wang, He Zhu, Wangchunshu Zhou, and Shuicheng Yan. Memevolve: Meta-evolution of agent memory systems. arXiv preprint arXiv:2512.18746, 2025g. — [arXiv:2512.18746](https://arxiv.org/abs/2512.18746) [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Haotian+Ren%2C+Chong+Zhan%2C+Zhenhong+Zhou%2C+Junhao+Wang%2C+He+Zhu%2C+Wangchunshu+Zhou%2C+and+Shuicheng+Yan%2E+Memevolve%3A+Meta%2Devolution+of+agent+memory+systems%2E+arXiv+preprint+arXiv%3A2512%2E18746%2C+2025)
333. Hanrong Zhang, Jingyuan Huang, Kai Mei, Yifei Yao, Zhenting Wang, Chenlu Zhan, Hongwei Wang, and Yongfeng Zhang. Agent security bench (asb): Formalizing and benchmarking attacks and defenses in llm-based agents. arXiv preprint arXiv:2410.02644, 2024b. — [arXiv:2410.02644](https://arxiv.org/abs/2410.02644) [find](https://scholar.google.com/scholar?q=Hanrong+Zhang%2C+Jingyuan+Huang%2C+Kai+Mei%2C+Yifei+Yao%2C+Zhenting+Wang%2C+Chenlu+Zhan%2C+Hongwei+Wang%2C+and+Yongfeng+Zhang%2E+Agent+security+bench+%28asb%29%3A+Formalizing+and+benchmarking+attacks+and+defenses+in+llm%2Dba)
334. Jenny Zhang, Shengran Hu, Cong Lu, Robert Lange, and Jeff Clune. [Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents](https://md.research.elamur.ai/free/en/papers/zhang-2025-darwin-godel-machine-open/). arXiv preprint arXiv:2505.22954, 2025h.
335. Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, et al. [Aflow: Automating agentic workflow generation](https://md.research.elamur.ai/free/en/papers/zhang-2024-aflow-automating-agentic-workflow/). arXiv preprint arXiv:2410.10762, 2024c.
336. Jiayi Zhang, Yiran Peng, Fanqi Kong, Cheng Yang, Yifan Wu, Zhaoyang Yu, Jinyu Xiang, Jianhao Ruan, Jinlin Wang, Maojia Song, HongZhang Liu, Xiangru Tang, Bang Liu, Chenglin Wu, and Yuyu Luo. Autoenv: Automated environments for measuring cross-environment agent learning. arXiv preprint arXiv:2511.193… — [arXiv:2511.19304](https://arxiv.org/abs/2511.19304) [find](https://scholar.google.com/scholar?q=Jiayi+Zhang%2C+Yiran+Peng%2C+Fanqi+Kong%2C+Cheng+Yang%2C+Yifan+Wu%2C+Zhaoyang+Yu%2C+Jinyu+Xiang%2C+Jianhao+Ruan%2C+Jinlin+Wang%2C+Maojia+Song%2C+HongZhang+Liu%2C+Xiangru+Tang%2C+Bang+Liu%2C+Chenglin+Wu%2C+and+Yuyu+Luo%2E+Autoenv%3A+)
337. Kongcheng Zhang, Qi Yao, Shunyu Liu, Yingjie Wang, Baisheng Lai, Jieping Ye, Mingli Song, and Dacheng Tao. Consistent paths lead to truth: Self-rewarding reinforcement learning for llm reasoning, 2025j. URL https://arxiv.org/abs/2506.08745. — [arXiv:2506.08745](https://arxiv.org/abs/2506.08745) [↗](https://arxiv.org/abs/2506.08745)
338. Mike Zhang, Amalie Pernille Dilling, Léon Gondelman, Niels Erik Ruan Lyngdorf, Euan D. Lindsay, and Johannes Bjerva. Sefl: Harnessing large language model agents to improve educational feedback systems. arXiv preprint arXiv:2502.12927, 2025k. URL https://arxiv.org/abs/2502.12927. — [arXiv:2502.12927](https://arxiv.org/abs/2502.12927) [↗](https://arxiv.org/abs/2502.12927)
339. Ningyu Zhang, Yunzhi Yao, Bozhong Tian, Peng Wang, Shumin Deng, Mengru Wang, Zekun Xi, Shengyu Mao, Jintian Zhang, Yuansheng Ni, et al. A comprehensive study of knowledge editing for large language models. arXiv preprint arXiv:2401.01286, 2024d. [find](https://scholar.google.com/scholar?q=Ningyu+Zhang%2C+Yunzhi+Yao%2C+Bozhong+Tian%2C+Peng+Wang%2C+Shumin+Deng%2C+Mengru+Wang%2C+Zekun+Xi%2C+Shengyu+Mao%2C+Jintian+Zhang%2C+Yuansheng+Ni%2C+et+al%2E+A+comprehensive+study+of+knowledge+editing+for+large+language+mo)
340. Peiyan Zhang, Haibo Jin, Leyang Hu, Xinnuo Li, Liying Kang, Man Luo, Yangqiu Song, and Haohan Wang. Revolve: Optimizing ai systems by tracking response evolution in textual optimization. arXiv preprint arXiv:2412.03092, 2024e. — [arXiv:2412.03092](https://arxiv.org/abs/2412.03092) [find](https://scholar.google.com/scholar?q=Peiyan+Zhang%2C+Haibo+Jin%2C+Leyang+Hu%2C+Xinnuo+Li%2C+Liying+Kang%2C+Man+Luo%2C+Yangqiu+Song%2C+and+Haohan+Wang%2E+Revolve%3A+Optimizing+ai+systems+by+tracking+response+evolution+in+textual+optimization%2E+arXiv+preprin)
341. Qiyuan Zhang, Fuyuan Lyu, Zexu Sun, Lei Wang, Weixu Zhang, Wenyue Hua, Haolun Wu, Zhihan Guo, Yufei Wang, Niklas Muennighoff, et al. [A survey on test-time scaling in large language models: What, how, where, and how well?](https://md.research.elamur.ai/free/en/papers/zhang-2025-survey-test-time-scaling-large/) arXiv preprint arXiv:2503.24235, 2025l.
342. Qizheng Zhang, Changran Hu, Shubhangi Upasani, Boyuan Ma, Fenglu Hong, Vamsidhar Kamanuru, Jay Rainton, Chen Wu, Mengmeng Ji, Hanchen Li, et al. [Agentic context engineering: Evolving contexts for self-improving language models](https://md.research.elamur.ai/free/en/papers/zhang-2025-agentic-context-engineering-evolving-contexts/). arXiv preprint arXiv:2510.04618, 2025m.
343. Shaokun Zhang, Jieyu Zhang, Jiale Liu, Linxin Song, Chi Wang, Ranjay Krishna, and Qingyun Wu. Offline training of language model agents with functions as learnable weights. In Forty-first International Conference on Machine Learning, 2024f. [find](https://scholar.google.com/scholar?q=Shaokun+Zhang%2C+Jieyu+Zhang%2C+Jiale+Liu%2C+Linxin+Song%2C+Chi+Wang%2C+Ranjay+Krishna%2C+and+Qingyun+Wu%2E+Offline+training+of+language+model+agents+with+functions+as+learnable+weights%2E+In+Forty%2Dfirst+Internationa)
344. Shaokun Zhang, Yi Dong, Jieyu Zhang, Jan Kautz, Bryan Catanzaro, Andrew Tao, Qingyun Wu, Zhiding Yu, and Guilin Liu. Nemotron-research-tool-n1: Exploring tool-using language models with reinforced reasoning. arXiv preprint arXiv:2505.00024, 2025n. — [arXiv:2505.00024](https://arxiv.org/abs/2505.00024) [find](https://scholar.google.com/scholar?q=Shaokun+Zhang%2C+Yi+Dong%2C+Jieyu+Zhang%2C+Jan+Kautz%2C+Bryan+Catanzaro%2C+Andrew+Tao%2C+Qingyun+Wu%2C+Zhiding+Yu%2C+and+Guilin+Liu%2E+Nemotron%2Dresearch%2Dtool%2Dn1%3A+Exploring+tool%2Dusing+language+models+with+reinforced+rea)
345. Xuemiao Zhang, Liangyu Xu, Feiyu Duan, Yongwei Zhou, Sirui Wang, Rongxiang Weng, Jingang Wang, and Xunliang Cai. Preference curriculum: Llms should always be pretrained on their preferred data. arXiv preprint arXiv:2501.13126, 2025o. [find](https://scholar.google.com/scholar?q=Xuemiao+Zhang%2C+Liangyu+Xu%2C+Feiyu+Duan%2C+Yongwei+Zhou%2C+Sirui+Wang%2C+Rongxiang+Weng%2C+Jingang+Wang%2C+and+Xunliang+Cai%2E+Preference+curriculum%3A+Llms+should+always+be+pretrained+on+their+preferred+data%2E+arXiv+)
346. Xueqiao Zhang, Chao Zhang, Jianwen Sun, Jun Xiao, Yi Yang, and Yawei Luo. Eduplanner: Llm-based multi-agent systems for customized and intelligent instructional design. arXiv preprint arXiv:2504.05370, 2025p. URL https://arxiv.org/abs/2504.05370. — [arXiv:2504.05370](https://arxiv.org/abs/2504.05370) [↗](https://arxiv.org/abs/2504.05370)
347. Yijing Zhang, Dyah Adila, Changho Shin, and Frederic Sala. Personalize your llm: Fake it then align it. arXiv preprint arXiv:2503.01048, 2025q. [find](https://scholar.google.com/scholar?q=Yijing+Zhang%2C+Dyah+Adila%2C+Changho+Shin%2C+and+Frederic+Sala%2E+Personalize+your+llm%3A+Fake+it+then+align+it%2E+arXiv+preprint+arXiv%3A2503%2E01048%2C+2025q%2E)
348. Yiqun Zhang, Peng Ye, Xiaocui Yang, Shi Feng, Shufei Zhang, Lei Bai, Wanli Ouyang, and Shuyue Hu. [Nature-inspired population-based evolution of large language models](https://md.research.elamur.ai/free/en/papers/zhang-2026-nature-inspired-population-based-evolution/). arXiv preprint arXiv:2503.01155, 2025r.
349. Yuanshuo Zhang, Yuchen Hou, Bohan Tang, Shuo Chen, Muhan Zhang, Xiaowen Dong, and Siheng Chen. Gnns as predictors of agentic workflow performances. arXiv preprint arXiv:2503.11301, 2025s. — [arXiv:2503.11301](https://arxiv.org/abs/2503.11301) [find](https://scholar.google.com/scholar?q=Yuanshuo+Zhang%2C+Yuchen+Hou%2C+Bohan+Tang%2C+Shuo+Chen%2C+Muhan+Zhang%2C+Xiaowen+Dong%2C+and+Siheng+Chen%2E+Gnns+as+predictors+of+agentic+workflow+performances%2E+arXiv+preprint+arXiv%3A2503%2E11301%2C+2025s%2E+%E2%80%94+%5BarXiv%3A250)
350. Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. A survey on the memory mechanism of large language model based agents. arXiv preprint arXiv:2404.13501, 2024g. [find](https://scholar.google.com/scholar?q=Zeyu+Zhang%2C+Xiaohe+Bo%2C+Chen+Ma%2C+Rui+Li%2C+Xu+Chen%2C+Quanyu+Dai%2C+Jieming+Zhu%2C+Zhenhua+Dong%2C+and+Ji%2DRong+Wen%2E+A+survey+on+the+memory+mechanism+of+large+language+model+based+agents%2E+arXiv+preprint+arXiv%3A240)
351. Zhehao Zhang, Ryan A Rossi, Branislav Kveton, Yijia Shao, Diyi Yang, Hamed Zamani, Franck Dernoncourt, Joe Barrow, Tong Yu, Sungchul Kim, et al. Personalization of [large language models: A survey](https://md.research.elamur.ai/free/en/papers/minaee-2024-large-language-models-survey/). arXiv preprint arXiv:2411.00027, 2024h.
352. Zhexin Zhang, Shiyao Cui, Yida Lu, Jingzhuo Zhou, Junxiao Yang, Hongning Wang, and Minlie Huang. Agent-safetybench: Evaluating the safety of llm agents. arXiv preprint arXiv:2412.14470, 2024i. — [arXiv:2412.14470](https://arxiv.org/abs/2412.14470) [find](https://scholar.google.com/scholar?q=Zhexin+Zhang%2C+Shiyao+Cui%2C+Yida+Lu%2C+Jingzhuo+Zhou%2C+Junxiao+Yang%2C+Hongning+Wang%2C+and+Minlie+Huang%2E+Agent%2Dsafetybench%3A+Evaluating+the+safety+of+llm+agents%2E+arXiv+preprint+arXiv%3A2412%2E14470%2C+2024i%2E+%E2%80%94+%5BarXi)
353. Zhexin Zhang, Junxiao Yang, Pei Ke, Shiyao Cui, Chujie Zheng, Hongning Wang, and Minlie Huang. Safe unlearning: A surprisingly effective and generalizable solution to defend against jailbreak attacks. arXiv preprint arXiv:2407.02855, 2024j. — [arXiv:2407.02855](https://arxiv.org/abs/2407.02855) [find](https://scholar.google.com/scholar?q=Zhexin+Zhang%2C+Junxiao+Yang%2C+Pei+Ke%2C+Shiyao+Cui%2C+Chujie+Zheng%2C+Hongning+Wang%2C+and+Minlie+Huang%2E+Safe+unlearning%3A+A+surprisingly+effective+and+generalizable+solution+to+defend+against+jailbreak+attacks%2E)
354. Zhongyue Zhang, Zijie Qiu, Yingcheng Wu, Shuya Li, Dingyan Wang, Zhuomin Zhou, Duo An, Yuhan Chen, Yu Li, Yongbo Wang, et al. Origene: A self-evolving virtual disease biologist automating therapeutic target discovery. bioRxiv, pp. 2025–06, 2025t. [find](https://scholar.google.com/scholar?q=Zhongyue+Zhang%2C+Zijie+Qiu%2C+Yingcheng+Wu%2C+Shuya+Li%2C+Dingyan+Wang%2C+Zhuomin+Zhou%2C+Duo+An%2C+Yuhan+Chen%2C+Yu+Li%2C+Yongbo+Wang%2C+et+al%2E+Origene%3A+A+self%2Devolving+virtual+disease+biologist+automating+therapeutic+)
355. Andrew Zhao, Daniel Huang, Quentin Xu, Matthieu Lin, Yong-Jin Liu, and Gao Huang. Expel: Llm agents are experiential learners. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pp. 19632–19642, 2024a. [find](https://scholar.google.com/scholar?q=Andrew+Zhao%2C+Daniel+Huang%2C+Quentin+Xu%2C+Matthieu+Lin%2C+Yong%2DJin+Liu%2C+and+Gao+Huang%2E+Expel%3A+Llm+agents+are+experiential+learners%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volume+)
356. Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, and Gao Huang. [Absolute zero: Reinforced self-play reasoning with zero data](https://md.research.elamur.ai/free/en/papers/zhao-2025-absolute-zero-reinforced-self-play/). arXiv preprint arXiv:2505.03335, 2025a.
357. Haiteng Zhao, Chang Ma, Guoyin Wang, Jing Su, Lingpeng Kong, Jingjing Xu, Zhi-Hong Deng, and Hongxia Yang. Empowering large language model agents through action learning. CoRR, abs/2402.15809, 2024b. — [arXiv:2402.15809](https://arxiv.org/abs/2402.15809) [find](https://scholar.google.com/scholar?q=Haiteng+Zhao%2C+Chang+Ma%2C+Guoyin+Wang%2C+Jing+Su%2C+Lingpeng+Kong%2C+Jingjing+Xu%2C+Zhi%2DHong+Deng%2C+and+Hongxia+Yang%2E+Empowering+large+language+model+agents+through+action+learning%2E+CoRR%2C+abs%2F2402%2E15809%2C+2024b%2E+)
358. Henry Hengyuan Zhao, Pan Zhou, and Mike Zheng Shou. Genixer: Empowering multimodal large language model as a powerful data generator. In European Conference on Computer Vision, pp. 129–147. Springer, 2024c. [find](https://scholar.google.com/scholar?q=Henry+Hengyuan+Zhao%2C+Pan+Zhou%2C+and+Mike+Zheng+Shou%2E+Genixer%3A+Empowering+multimodal+large+language+model+as+a+powerful+data+generator%2E+In+European+Conference+on+Computer+Vision%2C+pp%2E+129%E2%80%93147%2E+Springer%2C+)
359. Qianchuan Zhao, Yuxiang Xie, Wentao Wang, Jie Li, Lizhou Sha, Jialong Zhang, and Minlie Huang. Richelieu: Self-evolving LLM-based agents for AI diplomacy. arXiv preprint arXiv:2407.06813, 2024d. URL https://arxiv.org/abs/2407.06813. — [arXiv:2407.06813](https://arxiv.org/abs/2407.06813) [↗](https://arxiv.org/abs/2407.06813)
360. Wanjia Zhao, Mert Yuksekgonul, Shirley Wu, and James Zou. Sirius: Self-improving multi-agent systems via bootstrapped reasoning. arXiv preprint arXiv:2502.04780, 2025b. — [arXiv:2502.04780](https://arxiv.org/abs/2502.04780) [find](https://scholar.google.com/scholar?q=Wanjia+Zhao%2C+Mert+Yuksekgonul%2C+Shirley+Wu%2C+and+James+Zou%2E+Sirius%3A+Self%2Dimproving+multi%2Dagent+systems+via+bootstrapped+reasoning%2E+arXiv+preprint+arXiv%3A2502%2E04780%2C+2025b%2E+%E2%80%94+%5BarXiv%3A2502%2E04780%5D%28https%3A%2F%2Far)
361. Arman Zharmagambetov, Chuan Guo, Ivan Evtimov, Maya Pavlova, Ruslan Salakhutdinov, and Kamalika Chaudhuri. Agentdam: Privacy leakage evaluation for autonomous web agents. arXiv preprint arXiv:2503.09780, 2025. [find](https://scholar.google.com/scholar?q=Arman+Zharmagambetov%2C+Chuan+Guo%2C+Ivan+Evtimov%2C+Maya+Pavlova%2C+Ruslan+Salakhutdinov%2C+and+Kamalika+Chaudhuri%2E+Agentdam%3A+Privacy+leakage+evaluation+for+autonomous+web+agents%2E+arXiv+preprint+arXiv%3A2503%2E097)
362. Boyuan Zheng, Michael Y. Fatemi, Xiaolong Jin, Zora Zhiruo Wang, Apurva Gandhi, Yueqi Song, Yu Gu, Jayanth Srinivasa, Gaowen Liu, Graham Neubig, and Yu Su. Skillweaver: Web agents can self-improve by discovering and honing skills. CoRR, abs/2504.07079, 2025a. [find](https://scholar.google.com/scholar?q=Boyuan+Zheng%2C+Michael+Y%2E+Fatemi%2C+Xiaolong+Jin%2C+Zora+Zhiruo+Wang%2C+Apurva+Gandhi%2C+Yueqi+Song%2C+Yu+Gu%2C+Jayanth+Srinivasa%2C+Gaowen+Liu%2C+Graham+Neubig%2C+and+Yu+Su%2E+Skillweaver%3A+Web+agents+can+self%2Dimprove+by+)
363. Huaixiu Steven Zheng, Swaroop Mishra, Hugh Zhang, Xinyun Chen, Minmin Chen, Azade Nova, Le Hou, Heng-Tze Cheng, Quoc V Le, Ed H Chi, et al. Natural plan: Benchmarking llms on natural language planning. arXiv preprint arXiv:2406.04520, 2024a. [find](https://scholar.google.com/scholar?q=Huaixiu+Steven+Zheng%2C+Swaroop+Mishra%2C+Hugh+Zhang%2C+Xinyun+Chen%2C+Minmin+Chen%2C+Azade+Nova%2C+Le+Hou%2C+Heng%2DTze+Cheng%2C+Quoc+V+Le%2C+Ed+H+Chi%2C+et+al%2E+Natural+plan%3A+Benchmarking+llms+on+natural+language+planning)
364. Junhao Zheng, Xidi Cai, Qiuke Li, Duzhen Zhang, ZhongZhi Li, Yingying Zhang, Le Song, and Qianli Ma. Lifelongagentbench: Evaluating llm agents as lifelong learners. arXiv preprint arXiv:2505.11942, 2025b. — [arXiv:2505.11942](https://arxiv.org/abs/2505.11942) [find](https://scholar.google.com/scholar?q=Junhao+Zheng%2C+Xidi+Cai%2C+Qiuke+Li%2C+Duzhen+Zhang%2C+ZhongZhi+Li%2C+Yingying+Zhang%2C+Le+Song%2C+and+Qianli+Ma%2E+Lifelongagentbench%3A+Evaluating+llm+agents+as+lifelong+learners%2E+arXiv+preprint+arXiv%3A2505%2E11942%2C+20)
365. Junhao Zheng, Chengming Shi, Xidi Cai, Qiuke Li, Duzhen Zhang, Chenxing Li, Dong Yu, and Qianli Ma. Lifelong learning of large language model based agents: A roadmap. arXiv preprint arXiv:2501.07278, 2025c. — [arXiv:2501.07278](https://arxiv.org/abs/2501.07278) [find](https://scholar.google.com/scholar?q=Junhao+Zheng%2C+Chengming+Shi%2C+Xidi+Cai%2C+Qiuke+Li%2C+Duzhen+Zhang%2C+Chenxing+Li%2C+Dong+Yu%2C+and+Qianli+Ma%2E+Lifelong+learning+of+large+language+model+based+agents%3A+A+roadmap%2E+arXiv+preprint+arXiv%3A2501%2E07278%2C+)
366. Yuanhang Zheng, Peng Li, Wei Liu, Yang Liu, Jian Luan, and Bin Wang. Toolrerank: Adaptive and hierarchy-aware reranking for tool retrieval. In LREC/COLING, pp. 16263–16273. ELRA and ICCL, 2024b. [find](https://scholar.google.com/scholar?q=Yuanhang+Zheng%2C+Peng+Li%2C+Wei+Liu%2C+Yang+Liu%2C+Jian+Luan%2C+and+Bin+Wang%2E+Toolrerank%3A+Adaptive+and+hierarchy%2Daware+reranking+for+tool+retrieval%2E+In+LREC%2FCOLING%2C+pp%2E+16263%E2%80%9316273%2E+ELRA+and+ICCL%2C+2024b%2E)
367. Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. Memorybank: Enhancing large language models with long-term memory. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pp. 19724–19731, 2024. [find](https://scholar.google.com/scholar?q=Wanjun+Zhong%2C+Lianghong+Guo%2C+Qiqi+Gao%2C+He+Ye%2C+and+Yanlin+Wang%2E+Memorybank%3A+Enhancing+large+language+models+with+long%2Dterm+memory%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence%2C+volu)
368. Da-Wei Zhou, Hai-Long Sun, Jingyi Ning, Han-Jia Ye, and De-Chuan Zhan. Continual learning with pre-trained models: A survey. arXiv preprint arXiv:2401.16386, 2024a. — [arXiv:2401.16386](https://arxiv.org/abs/2401.16386) [find](https://scholar.google.com/scholar?q=Da%2DWei+Zhou%2C+Hai%2DLong+Sun%2C+Jingyi+Ning%2C+Han%2DJia+Ye%2C+and+De%2DChuan+Zhan%2E+Continual+learning+with+pre%2Dtrained+models%3A+A+survey%2E+arXiv+preprint+arXiv%3A2401%2E16386%2C+2024a%2E+%E2%80%94+%5BarXiv%3A2401%2E16386%5D%28https%3A%2F%2Farxiv%2E)
369. Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić, Anna Korhonen, and Sercan Ö. Arık. Multi-agent design: Optimizing agents with better prompts and topologies, 2025a. URL https://arxiv.org/abs/2502.02533. — [arXiv:2502.02533](https://arxiv.org/abs/2502.02533) [↗](https://arxiv.org/abs/2502.02533)
370. Huichi Zhou, Yihang Chen, Siyuan Guo, Xue Yan, Kin Hei Lee, Zihan Wang, Ka Yiu Lee, Guchun Zhang, Kun Shao, Linyi Yang, et al. Memento: Fine-tuning llm agents without fine-tuning llms. arXiv preprint arXiv:2508.16153, 2025b. — [arXiv:2508.16153](https://arxiv.org/abs/2508.16153) [find](https://scholar.google.com/scholar?q=Huichi+Zhou%2C+Yihang+Chen%2C+Siyuan+Guo%2C+Xue+Yan%2C+Kin+Hei+Lee%2C+Zihan+Wang%2C+Ka+Yiu+Lee%2C+Guchun+Zhang%2C+Kun+Shao%2C+Linyi+Yang%2C+et+al%2E+Memento%3A+Fine%2Dtuning+llm+agents+without+fine%2Dtuning+llms%2E+arXiv+preprint+)
371. Jijie Zhou, Eryue Xu, Yaoyao Wu, and Tianshi Li. Rescriber: Smaller-llm-powered user-led data minimization for llm-based chatbots. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, pp. 1–28, 2025c. [find](https://scholar.google.com/scholar?q=Jijie+Zhou%2C+Eryue+Xu%2C+Yaoyao+Wu%2C+and+Tianshi+Li%2E+Rescriber%3A+Smaller%2Dllm%2Dpowered+user%2Dled+data+minimization+for+llm%2Dbased+chatbots%2E+In+Proceedings+of+the+2025+CHI+Conference+on+Human+Factors+in+Computi)
372. Shuyan Zhou, Frank F Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, et al. [Webarena: A realistic web environment for building autonomous agents](https://md.research.elamur.ai/free/en/papers/zhou-2023-webarena-realistic-web-environment-building/). arXiv preprint arXiv:2307.13854, 2023.
373. Wangchunshu Zhou, Yixin Ou, Shengwei Ding, Long Li, Jialong Wu, Tiannan Wang, Jiamin Chen, Shuai Wang, Xiaohua Xu, Ningyu Zhang, et al. [Symbolic learning enables self-evolving agents](https://md.research.elamur.ai/free/en/papers/zhou-2024-symbolic-learning-enables-self-evolving/). arXiv preprint arXiv:2406.18532, 2024b.
374. Xueyang Zhou, Weidong Wang, Lin Lu, Jiawen Shi, Guiyao Tie, Yongtian Xu, Lixing Chen, Pan Zhou, Neil Zhenqiang Gong, and Lichao Sun. Automating safety enhancement for llm-based agents with synthetic risk scenarios. arXiv preprint arXiv:2505.17735, 2025d. — [arXiv:2505.17735](https://arxiv.org/abs/2505.17735) [find](https://scholar.google.com/scholar?q=Xueyang+Zhou%2C+Weidong+Wang%2C+Lin+Lu%2C+Jiawen+Shi%2C+Guiyao+Tie%2C+Yongtian+Xu%2C+Lixing+Chen%2C+Pan+Zhou%2C+Neil+Zhenqiang+Gong%2C+and+Lichao+Sun%2E+Automating+safety+enhancement+for+llm%2Dbased+agents+with+synthetic+r)
375. Yifei Zhou, Sergey Levine, Jason Weston, Xian Li, and Sainbayar Sukhbaatar. Self-challenging language model agents, 2025e. URL https://arxiv.org/abs/2506.01716. — [arXiv:2506.01716](https://arxiv.org/abs/2506.01716) [↗](https://arxiv.org/abs/2506.01716)
376. Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han, Keiran Paster, Silviu Pitis, Harris Chan, and Jimmy Ba. [Large language models are human-level prompt engineers](https://md.research.elamur.ai/free/en/papers/zhou-2022-large-language-models-human-level/). In The Eleventh International Conference on Learning Representations, 2022.
377. Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Xiangru Tang, Heng Ji, et al. [Multiagentbench: Evaluating the collaboration and competition of llm agents](https://md.research.elamur.ai/free/en/papers/zhu-2025-multiagentbench-evaluating-collaboration-competition/). arXiv preprint arXiv:2503.01935, 2025.
378. Yangyang Zhuang, Wenjia Jiang, Jiayu Zhang, Ze Yang, Joey Tianyi Zhou, and Chi Zhang. Learning to be a doctor: Searching for effective medical agent architectures. arXiv preprint arXiv:2504.11301, 2025. — [arXiv:2504.11301](https://arxiv.org/abs/2504.11301) [find](https://scholar.google.com/scholar?q=Yangyang+Zhuang%2C+Wenjia+Jiang%2C+Jiayu+Zhang%2C+Ze+Yang%2C+Joey+Tianyi+Zhou%2C+and+Chi+Zhang%2E+Learning+to+be+a+doctor%3A+Searching+for+effective+medical+agent+architectures%2E+arXiv+preprint+arXiv%3A2504%2E11301%2C+202)
379. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. Gptswarm: [Language agents as optimizable graphs](https://md.research.elamur.ai/free/en/papers/zhuge-2024-language-agents-optimizable-graphs/). In ICML. OpenReview.net, 2024.
380. Andy Zou, Long Phan, Justin Wang, Derek Duenas, Maxwell Lin, Maksym Andriushchenko, J Zico Kolter, Matt Fredrikson, and Dan Hendrycks. [Improving alignment and robustness with circuit breakers](https://md.research.elamur.ai/free/en/papers/zou-2024-improving-alignment-robustness-circuit-breakers/). In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024.
381. Yuxin Zuo, Kaiyan Zhang, Li Sheng, Shang Qu, Ganqu Cui, Xuekai Zhu, Haozhan Li, Yuchen Zhang, Xinwei Long, Ermo Hua, et al. [Ttrl: Test-time reinforcement learning](https://md.research.elamur.ai/free/en/papers/zuo-2025-ttrl-test-time-reinforcement-learning/). arXiv preprint arXiv:2504.16084, 2025.
382. Adam Zweiger, Jyothish Pari, Han Guo, Ekin Akyürek, Yoon Kim, and Pulkit Agrawal. Self-adapting language models. arXiv preprint arXiv:2506.10943, 2025. — [arXiv:2506.10943](https://arxiv.org/abs/2506.10943) [find](https://scholar.google.com/scholar?q=Adam+Zweiger%2C+Jyothish+Pari%2C+Han+Guo%2C+Ekin+Aky%C3%BCrek%2C+Yoon+Kim%2C+and+Pulkit+Agrawal%2E+Self%2Dadapting+language+models%2E+arXiv+preprint+arXiv%3A2506%2E10943%2C+2025%2E+%E2%80%94+%5BarXiv%3A2506%2E10943%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E)

*Updated 3 November 2026*