---
title: "MemSearcher — paper by Yuan et al. (2026)"
description: "MemSearcher replaces this ever-growing history: at each step the model sees only the question and a short natural-language… 57 references."
authors: ["Qianhao Yuan", "Jie Lou", "Zichao Li", "Jiawei Chen", "Yaojie Lu", "Hongyu Lin", "Le Sun", "Debing Zhang", "Xianpei Han"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.736/"
doi: "10.18653/v1/2026.findings-acl.736"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yuan-2026-memsearcher-iterative-memory-integration-search/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yuan-2026-memsearcher-iterative-memory-integration-search/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/) / MemSearcher: Iterative Memory Integration for Search Agent via End-to-End Reinforcement Learning

# MemSearcher: Iterative Memory Integration for Search Agent via End-to-End Reinforcement Learning

**Authors:** [Qianhao Yuan](https://md.research.elamur.ai/free/en/authors/qianhao-yuan/), Jie Lou, [Zichao Li](https://md.research.elamur.ai/free/en/authors/zichao-li/), [Jiawei Chen](https://md.research.elamur.ai/free/en/authors/jiawei-chen/), [Yaojie Lu](https://md.research.elamur.ai/free/en/authors/yaojie-lu/), [Hongyu Lin](https://md.research.elamur.ai/free/en/authors/hongyu-lin/), [Le Sun](https://md.research.elamur.ai/free/en/authors/le-sun/), [Debing Zhang](https://md.research.elamur.ai/free/en/authors/debing-zhang/) and [Xianpei Han](https://md.research.elamur.ai/free/en/authors/xianpei-han/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.736/) · [PDF](https://aclanthology.org/2026.findings-acl.736.pdf) · [DOI 10.18653/v1/2026.findings-acl.736](https://doi.org/10.18653/v1/2026.findings-acl.736) · [OpenAlex](https://openalex.org/W7166825679)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Search agents built on LLMs usually follow the ReAct pattern. Every thought, tool call and retrieved passage is appended to the prompt, so context grows with each turn. The inputs fill up with irrelevant retrieved text, and compute and GPU memory costs rise. MemSearcher replaces this ever-growing history: at each step the model sees only the question and a short natural-language memory, capped at a fixed token budget. After each search result arrives, the same backbone LLM rewrites the memory, keeping facts that help answer the question and dropping the rest.

Each turn of a trajectory therefore runs under its own context, which standard GRPO does not handle directly. The authors add multi-context GRPO, which assigns the trajectory-level advantage to every turn and optimizes the turns separately. This allows end-to-end RL without annotated trajectories.

Across seven public knowledge-acquisition benchmarks, MemSearcher beats ReAct-style baselines while its token count stays nearly flat. Search agents can thus run in windows under 4K tokens, which suits resource-limited deployments.

## Key points
- **Cost comparison with ReAct:**
  - ReAct context length grows as O(n) in the number of turns, and total FLOPs grow as O(n²).
  - MemSearcher keeps context at O(1) and per-turn FLOPs constant, so total compute grows as O(n).
- **Comparison baselines:** ReAct-based agents such as Search-R1 and ReSearch.
- **Prompt format:** the model reads `<question>` and `<memory>` and writes `<think>` and `<tool_call>`. Tool output arrives in `<tool_response>`, and final answers go in `\boxed{}`.
- **Memory length:** the default cap is 1,024 tokens, and the ablation tested 256–2,048 tokens on 7B and 14B models.
  - On Bamboogle, results already saturate at 256 tokens.
  - On Musique, accuracy keeps rising up to 1,024 tokens.
  - Overall, mid-sized memories gave the best trade-off.
- **Limitations named by the authors:** richer memory designs (RAG-like or structured) remain untested, and multi-context GRPO may suffer from length bias. Code and models are promised at github.com/icip-cas/MemSearcher.

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

## Institutions

- [Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/government/chinese-academy-of-sciences/) — Government body, Beijing, China · 246 works · 24,951 citations
- [University of Chinese Academy of Sciences](https://md.research.elamur.ai/free/en/universities/university-of-chinese-academy-of-sciences/) — University, Beijing, China · 188 works · 8,743 citations
- [Institute of Software](https://md.research.elamur.ai/free/en/labs/institute-of-software/) — Research institute, Beijing, China · 27 works · 4,979 citations
- [Xiaohongshu (Little Red Book)](https://md.research.elamur.ai/free/en/companies/xiaohongshu-little-red-book/) — Company, Shanghai, China · 13 works · 107 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🗄️ Information Systems](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · 1,730 works

## Cite

Cite as: Qianhao Yuan, Jie Lou, Zichao Li, Jiawei Chen, Yaojie Lu, Hongyu Lin, Le Sun, Debing Zhang and Xianpei Han. 2026. MemSearcher: Iterative Memory Integration for Search Agent via End-to-End Reinforcement Learning. Findings of the Association for Computational Linguistics: ACL 2026.

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

```bibtex
@inproceedings{yuan2026memsearcher,
  title = {{MemSearcher: Iterative Memory Integration for Search Agent via End-to-End Reinforcement Learning}},
  author = {Qianhao Yuan, Jie Lou, Zichao Li, Jiawei Chen, Yaojie Lu, Hongyu Lin, Le Sun, Debing Zhang and Xianpei Han},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.736},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.736}
}
```

- [← previous Memory-Guided Hard Data Augmentation for Multimodal Named Entity Recognition](https://md.research.elamur.ai/free/en/papers/liu-2026-memory-guided-hard-data-augmentation/)
- [next → MemWeaver: Weaving Hybrid Memories for Traceable Long-Horizon Agentic Reasoning](https://md.research.elamur.ai/free/en/papers/ye-2026-memweaver-weaving-hybrid-memories-traceable/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/)

## References

57 references, 33 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). arXiv preprint arXiv:2303.08774.
2. Jiawei Chen, Xinyan Guan, Qianhao Yuan, Guozhao Mo, Weixiang Zhou, Yaojie Lu, Hongyu Lin, Ben He, Le Sun, and Xianpei Han. 2025a. Consistentchat: Building skeleton-guided consistent dialogues for large language models from scratch. arXiv preprint arXiv:2506.03558. — [arXiv:2506.03558](https://arxiv.org/abs/2506.03558) [find](https://scholar.google.com/scholar?q=Jiawei+Chen%2C+Xinyan+Guan%2C+Qianhao+Yuan%2C+Guozhao+Mo%2C+Weixiang+Zhou%2C+Yaojie+Lu%2C+Hongyu+Lin%2C+Ben+He%2C+Le+Sun%2C+and+Xianpei+Han%2E+2025a%2E+Consistentchat%3A+Building+skeleton%2Dguided+consistent+dialogues+for+larg)
3. Mingyang Chen, Tianpeng Li, Haoze Sun, Yijie Zhou, Chenzheng Zhu, Haofen Wang, Jeff Z Pan, Wen Zhang, Huajun Chen, Fan Yang, and 1 others. 2025b. [Learning to reason with search for llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/chen-2025-research-learning-reason-search-llms/). arXiv preprint arXiv:2503.19470.
4. Prateek Chhikara, Dev Khant, Saket Aryan, Taranjeet Singh, and Deshraj Yadav. 2025. [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.
5. Xanh Ho, Anh-Khoa Duong Nguyen, Saku Sugawara, and Akiko Aizawa. 2020. [Constructing a multi-hop qa dataset for comprehensive evaluation of reasoning steps](https://md.research.elamur.ai/free/en/papers/ho-2020-constructing-multi-hop-qa-dataset/). arXiv preprint arXiv:2011.01060.
6. Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman, Shantanu Acharya, Dima Rekesh, Fei Jia, Yang Zhang, and Boris Ginsburg. 2024. [Ruler: What’s the real context size of your long-context language models?](https://md.research.elamur.ai/free/en/papers/hsieh-2024-ruler-s-real-context-size/) arXiv preprint arXiv:2404.06654.
7. Bernal Jimenez Gutierrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, and Yu Su. 2024. [Hipporag: Neurobiologically inspired long-term memory for large language models](https://md.research.elamur.ai/free/en/papers/gutierrez-2024-hipporag-neurobiologically-inspired-long-term/). Advances in Neural Information Processing Systems, 37:59532–59569.
8. Bowen Jin, Hansi Zeng, Zhenrui Yue, Jinsung Yoon, Sercan Arik, Dong Wang, Hamed Zamani, and Jiawei Han. 2025. [Search-r1: Training llms to reason and leverage search engines with reinforcement learning](https://md.research.elamur.ai/free/en/papers/jin-2025-search-r1-training-llms-reason/). arXiv preprint arXiv:2503.09516.
9. Mingyu Jin, Weidi Luo, Sitao Cheng, Xinyi Wang, Wenyue Hua, Ruixiang Tang, William Yang Wang, and Yongfeng Zhang. 2024. [Disentangling memory and reasoning ability in large language models](https://md.research.elamur.ai/free/en/papers/jin-2025-disentangling-memory-reasoning-ability-large/). arXiv preprint arXiv:2411.13504.
10. Mandar Joshi, Eunsol Choi, Daniel S Weld, and Luke Zettlemoyer. 2017. [Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension](https://md.research.elamur.ai/free/en/papers/joshi-2017-triviaqa-large-scale-distantly-supervised/). arXiv preprint arXiv:1705.03551.
11. Vladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick SH Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, and Wen-tau Yih. 2020. [Dense passage retrieval for open-domain question answering](https://md.research.elamur.ai/free/en/papers/karpukhin-2020-dense-passage-retrieval-open-domain/). In EMNLP (1), pages 6769–6781.
12. Tom Kwiatkowski, Jennimaria Palomaki, Olivia Redfield, Michael Collins, Ankur Parikh, Chris Alberti, Danielle Epstein, Illia Polosukhin, Jacob Devlin, Kenton Lee, and 1 others. 2019. [Natural questions: a benchmark for question answering research](https://md.research.elamur.ai/free/en/papers/kwiatkowski-2019-natural-questions-benchmark-question-answering/). Transactions of the Association for Computational Lin…
13. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. [Retrieval-augmented generation for knowledge-intensive nlp tasks](https://md.research.elamur.ai/free/en/papers/lewis-2020-retrieval-augmented-generation-knowledge-intensive/). Advances in neural information processing systems, 33:9459–…
14. Qwen, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, and 24 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15… [find](https://scholar.google.com/scholar?q=Qwen%2C+An+Yang%2C+Baosong+Yang%2C+Beichen+Zhang%2C+Binyuan+Hui%2C+Bo+Zheng%2C+Bowen+Yu%2C+Chengyuan+Li%2C+Dayiheng+Liu%2C+Fei+Huang%2C+Haoran+Wei%2C+Huan+Lin%2C+Jian+Yang%2C+Jianhong+Tu%2C+Jianwei+Zhang%2C+Jianxin+Yang%2C+Jiaxi+Yan)
15. Xiaoxi Li, Guanting Dong, Jiajie Jin, Yuyao Zhang, Yujia Zhou, Yutao Zhu, Peitian Zhang, and Zhicheng Dou. 2025. [Search-o1: Agentic search-enhanced large reasoning models](https://md.research.elamur.ai/free/en/papers/li-2025-search-o1-agentic-search-enhanced/). arXiv preprint arXiv:2501.05366.
16. Preston Rasmussen, Pavlo Paliychuk, Travis Beauvais, Jack Ryan, and Daniel Chalef. 2025. [Zep: a temporal knowledge graph architecture for agent memory](https://md.research.elamur.ai/free/en/papers/rasmussen-2025-zep-temporal-knowledge-graph-architecture/). arXiv preprint arXiv:2501.13956.
17. Yinheng Li, Shaofei Wang, Han Ding, and Hang Chen. 2023. Large language models in finance: A survey. In Proceedings of the fourth ACM international conference on AI in finance, pages 374–382. [find](https://scholar.google.com/scholar?q=Yinheng+Li%2C+Shaofei+Wang%2C+Han+Ding%2C+and+Hang+Chen%2E+2023%2E+Large+language+models+in+finance%3A+A+survey%2E+In+Proceedings+of+the+fourth+ACM+international+conference+on+AI+in+finance%2C+pages+374%E2%80%93382%2E)
18. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+2017%2E+Proximal+policy+optimization+algorithms%2E+arXiv+preprint+arXiv%3A1707%2E06347%2E)
19. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. 2023. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). arXiv preprint arXiv:2307.03172.
20. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, and 1 others. 2024. [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.
21. Alex Mallen, Akari Asai, Victor Zhong, Rajarshi Das, Hannaneh Hajishirzi, and Daniel Khashabi. 2022. When not to trust language models: Investigating effectiveness and limitations of parametric and non-parametric memories. arXiv preprint arXiv:2212.10511, 7. [find](https://scholar.google.com/scholar?q=Alex+Mallen%2C+Akari+Asai%2C+Victor+Zhong%2C+Rajarshi+Das%2C+Hannaneh+Hajishirzi%2C+and+Daniel+Khashabi%2E+2022%2E+When+not+to+trust+language+models%3A+Investigating+effectiveness+and+limitations+of+parametric+and+no)
22. Guangming Sheng, Chi Zhang, Zilingfeng Ye, Xibin Wu, Wang Zhang, Ru Zhang, Yanghua Peng, Haibin Lin, and Chuan Wu. 2025. [Hybridflow: A flexible and efficient rlhf framework](https://md.research.elamur.ai/free/en/papers/sheng-2024-hybridflow-flexible-efficient-rlhf-framework/). In Proceedings of the Twentieth European Conference on Computer Systems, pages 1279–1297.
23. Jianbiao Mei, Tao Hu, Daocheng Fu, Licheng Wen, Xuemeng Yang, Rong Wu, Pinlong Cai, Xinyu Cai, Xing Gao, Yu Yang, and 1 others. 2025. O 2 -searcher: A searching-based agent model for open-domain open-ended question answering. arXiv preprint arXiv:2505.16582. — [arXiv:2505.16582](https://arxiv.org/abs/2505.16582) [find](https://scholar.google.com/scholar?q=Jianbiao+Mei%2C+Tao+Hu%2C+Daocheng+Fu%2C+Licheng+Wen%2C+Xuemeng+Yang%2C+Rong+Wu%2C+Pinlong+Cai%2C+Xinyu+Cai%2C+Xing+Gao%2C+Yu+Yang%2C+and+1+others%2E+2025%2E+O+2+%2Dsearcher%3A+A+searching%2Dbased+agent+model+for+open%2Ddomain+open%2D)
24. Yaorui Shi, Sihang Li, Chang Wu, Zhiyuan Liu, Junfeng Fang, Hengxing Cai, An Zhang, and Xiang Wang. 2025. [Search and refine during think: Autonomous retrieval-augmented reasoning of llms](https://md.research.elamur.ai/free/en/papers/shi-2025-search-refine-during-think-facilitating/). arXiv preprint arXiv:2505.11277.
25. Xin Men, Mingyu Xu, Qingyu Zhang, Qianhao Yuan, Bingning Wang, Hongyu Lin, Yaojie Lu, Xianpei Han, and Weipeng Chen. 2025. [Shortgpt: Layers in large language models are more redundant than you expect](https://md.research.elamur.ai/free/en/papers/men-2024-shortgpt-layers-large-language-models/). In Findings of the Association for Computational Linguistics: ACL 2025, pages 20192–20204.
26. Guozhao Mo, Wenliang Zhong, Jiawei Chen, Qianhao Yuan, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, and Le Sun. 2025. Livemcpbench: Can agents navigate an ocean of mcp tools? arXiv preprint arXiv:2508.01780. — [arXiv:2508.01780](https://arxiv.org/abs/2508.01780) [find](https://scholar.google.com/scholar?q=Guozhao+Mo%2C+Wenliang+Zhong%2C+Jiawei+Chen%2C+Qianhao+Yuan%2C+Xuanang+Chen%2C+Yaojie+Lu%2C+Hongyu+Lin%2C+Ben+He%2C+Xianpei+Han%2C+and+Le+Sun%2E+2025%2E+Livemcpbench%3A+Can+agents+navigate+an+ocean+of+mcp+tools%3F+arXiv+prepri)
27. José I Orlicki. 2025. Beyond words: A latent memory approach to internal reasoning in llms. arXiv preprint arXiv:2502.21030. — [arXiv:2502.21030](https://arxiv.org/abs/2502.21030) [find](https://scholar.google.com/scholar?q=Jos%C3%A9+I+Orlicki%2E+2025%2E+Beyond+words%3A+A+latent+memory+approach+to+internal+reasoning+in+llms%2E+arXiv+preprint+arXiv%3A2502%2E21030%2E+%E2%80%94+%5BarXiv%3A2502%2E21030%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2502%2E21030%29)
28. Cheng Peng, Xi Yang, Aokun Chen, Kaleb E Smith, Nima PourNejatian, Anthony B Costa, Cheryl Martin, Mona G Flores, Ying Zhang, Tanja Magoc, and 1 others. 2023. A study of generative large language model for medical research and healthcare. NPJ digital medicine, 6(1):210. [find](https://scholar.google.com/scholar?q=Cheng+Peng%2C+Xi+Yang%2C+Aokun+Chen%2C+Kaleb+E+Smith%2C+Nima+PourNejatian%2C+Anthony+B+Costa%2C+Cheryl+Martin%2C+Mona+G+Flores%2C+Ying+Zhang%2C+Tanja+Magoc%2C+and+1+others%2E+2023%2E+A+study+of+generative+large+language+mode)
29. Ofir Press, Muru Zhang, Sewon Min, Ludwig Schmidt, Noah A Smith, and Mike Lewis. 2022. Measuring and narrowing the compositionality gap in language models. arXiv preprint arXiv:2210.03350. [find](https://scholar.google.com/scholar?q=Ofir+Press%2C+Muru+Zhang%2C+Sewon+Min%2C+Ludwig+Schmidt%2C+Noah+A+Smith%2C+and+Mike+Lewis%2E+2022%2E+Measuring+and+narrowing+the+compositionality+gap+in+language+models%2E+arXiv+preprint+arXiv%3A2210%2E03350%2E)
30. Huatong Song, Jinhao Jiang, Yingqian Min, Jie Chen, Zhipeng Chen, Wayne Xin Zhao, Lei Fang, and Ji-Rong Wen. 2025. [R1-searcher: Incentivizing the search capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/song-2025-r1-searcher-incentivizing-search/). arXiv preprint arXiv:2503.05592.
31. Hao Sun, Zile Qiao, Jiayan Guo, Xuanbo Fan, Yingyan Hou, Yong Jiang, Pengjun Xie, Yan Zhang, Fei Huang, and Jingren Zhou. 2025. [Zerosearch: Incentivize the search capability of llms without searching](https://md.research.elamur.ai/free/en/papers/sun-2025-zerosearch-incentivize-search-capability-llms/). arXiv preprint arXiv:2505.04588.
32. Richard S Sutton, Andrew G Barto, and 1 others. 1998. Reinforcement learning: An introduction, volume 1. MIT press Cambridge. [find](https://scholar.google.com/scholar?q=Richard+S+Sutton%2C+Andrew+G+Barto%2C+and+1+others%2E+1998%2E+Reinforcement+learning%3A+An+introduction%2C+volume+1%2E+MIT+press+Cambridge%2E)
33. Zhengwei Tao, Jialong Wu, Wenbiao Yin, Junkai Zhang, Baixuan Li, Haiyang Shen, Kuan Li, Liwen Zhang, Xinyu Wang, Yong Jiang, and 1 others. 2025. Webshaper: Agentically data synthesizing via information-seeking formalization. arXiv preprint arXiv:2507.15061. — [arXiv:2507.15061](https://arxiv.org/abs/2507.15061) [find](https://scholar.google.com/scholar?q=Zhengwei+Tao%2C+Jialong+Wu%2C+Wenbiao+Yin%2C+Junkai+Zhang%2C+Baixuan+Li%2C+Haiyang+Shen%2C+Kuan+Li%2C+Liwen+Zhang%2C+Xinyu+Wang%2C+Yong+Jiang%2C+and+1+others%2E+2025%2E+Webshaper%3A+Agentically+data+synthesizing+via+informatio)
34. Harsh Trivedi, Niranjan Balasubramanian, Tushar Khot, and Ashish Sabharwal. 2022. Musique: Multi-hop questions via single-hop question composition. Transactions of the Association for Computational Linguistics, 10:539–554. [find](https://scholar.google.com/scholar?q=Harsh+Trivedi%2C+Niranjan+Balasubramanian%2C+Tushar+Khot%2C+and+Ashish+Sabharwal%2E+2022%2E+Musique%3A+Multi%2Dhop+questions+via+single%2Dhop+question+composition%2E+Transactions+of+the+Association+for+Computational+Li)
35. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, and Furu Wei. 2022. [Text embeddings by weakly-supervised contrastive pre-training](https://md.research.elamur.ai/free/en/papers/wang-2022-text-embeddings-weakly-supervised-contrastive/). arXiv preprint arXiv:2212.03533.
36. Yu Wang, Dmitry Krotov, Yuanzhe Hu, Yifan Gao, Wangchunshu Zhou, Julian McAuley, Dan Gutfreund, Rogerio Feris, and Zexue He. 2025. M+: Extending memoryllm with scalable long-term memory. arXiv preprint arXiv:2502.00592. [find](https://scholar.google.com/scholar?q=Yu+Wang%2C+Dmitry+Krotov%2C+Yuanzhe+Hu%2C+Yifan+Gao%2C+Wangchunshu+Zhou%2C+Julian+McAuley%2C+Dan+Gutfreund%2C+Rogerio+Feris%2C+and+Zexue+He%2E+2025%2E+M%2B%3A+Extending+memoryllm+with+scalable+long%2Dterm+memory%2E+arXiv+preprin)
37. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in neural information processing systems, 35:24824– 24837.
38. Di Wu, Hongwei Wang, Wenhao Yu, Yuwei Zhang, Kai-Wei Chang, and Dong Yu. 2024. [Longmemeval: Benchmarking chat assistants on long-term interactive memory](https://md.research.elamur.ai/free/en/papers/wu-2024-longmemeval-benchmarking-chat-assistants-long/). arXiv preprint arXiv:2410.10813.
39. Jialong Wu, Baixuan Li, Runnan Fang, Wenbiao Yin, Liwen Zhang, Zhengwei Tao, Dingchu Zhang, Zekun Xi, Gang Fu, Yong Jiang, and 1 others. 2025. [Webdancer: Towards autonomous information seeking agency](https://md.research.elamur.ai/free/en/papers/wu-2025-webdancer-towards-autonomous-information-seeking/). arXiv preprint arXiv:2505.22648.
40. Guangzhi Xiong, Qiao Jin, Xiao Wang, Yin Fang, Haolin Liu, Yifan Yang, Fangyuan Chen, Zhixing Song, Dengyu Wang, Minjia Zhang, and 1 others. 2025. Rag-gym: Optimizing reasoning and search agents with process supervision. arXiv preprint arXiv:2502.13957. — [arXiv:2502.13957](https://arxiv.org/abs/2502.13957) [find](https://scholar.google.com/scholar?q=Guangzhi+Xiong%2C+Qiao+Jin%2C+Xiao+Wang%2C+Yin+Fang%2C+Haolin+Liu%2C+Yifan+Yang%2C+Fangyuan+Chen%2C+Zhixing+Song%2C+Dengyu+Wang%2C+Minjia+Zhang%2C+and+1+others%2E+2025%2E+Rag%2Dgym%3A+Optimizing+reasoning+and+search+agents+with+)
41. Wenhao Yu, Dan Iter, Shuohang Wang, Yichong Xu, Mingxuan Ju, Soumya Sanyal, Chenguang Zhu, Michael Zeng, and Meng Jiang. 2022. [Generate rather than retrieve: Large language models are strong context generators](https://md.research.elamur.ai/free/en/papers/yu-2022-generate-rather-than-retrieve-large/). arXiv preprint arXiv:2209.10063.
42. Qianhao Yuan, Yanjiang Liu, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, and Le Sun. 2025a. Saisa: Towards multimodal large language models with both training and inference efficiency. arXiv preprint arXiv:2502.02458. — [arXiv:2502.02458](https://arxiv.org/abs/2502.02458) [find](https://scholar.google.com/scholar?q=Qianhao+Yuan%2C+Yanjiang+Liu%2C+Yaojie+Lu%2C+Hongyu+Lin%2C+Ben+He%2C+Xianpei+Han%2C+and+Le+Sun%2E+2025a%2E+Saisa%3A+Towards+multimodal+large+language+models+with+both+training+and+inference+efficiency%2E+arXiv+preprint+a)
43. Qianhao Yuan, Qingyu Zhang, Yanjiang Liu, Jiawei Chen, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, and Le Sun. 2025b. Shortv: Efficient multimodal large language models by freezing visual tokens in ineffective layers. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pag… [find](https://scholar.google.com/scholar?q=Qianhao+Yuan%2C+Qingyu+Zhang%2C+Yanjiang+Liu%2C+Jiawei+Chen%2C+Yaojie+Lu%2C+Hongyu+Lin%2C+Jia+Zheng%2C+Xianpei+Han%2C+and+Le+Sun%2E+2025b%2E+Shortv%3A+Efficient+multimodal+large+language+models+by+freezing+visual+tokens+in)
44. Zhenrui Yue, Honglei Zhuang, Aijun Bai, Kai Hui, Rolf Jagerman, Hansi Zeng, Zhen Qin, Dong Wang, Xuanhui Wang, and Michael Bendersky. 2024. Inference scaling for long-context retrieval augmented generation. arXiv preprint arXiv:2410.04343. — [arXiv:2410.04343](https://arxiv.org/abs/2410.04343) [find](https://scholar.google.com/scholar?q=Zhenrui+Yue%2C+Honglei+Zhuang%2C+Aijun+Bai%2C+Kai+Hui%2C+Rolf+Jagerman%2C+Hansi+Zeng%2C+Zhen+Qin%2C+Dong+Wang%2C+Xuanhui+Wang%2C+and+Michael+Bendersky%2E+2024%2E+Inference+scaling+for+long%2Dcontext+retrieval+augmented+gener)
45. Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, and 1 others. 2025. [Glm-4.5: Agentic, reasoning, and coding (arc) foundation models](https://md.research.elamur.ai/free/en/papers/team-2025-4-glm-4-5-agentic/). arXiv preprint arXiv:2508.06471.
46. Ruihong Zeng, Jinyuan Fang, Siwei Liu, and Zaiqiao Meng. 2024. On the structural memory of llm agents. arXiv preprint arXiv:2412.15266. — [arXiv:2412.15266](https://arxiv.org/abs/2412.15266) [find](https://scholar.google.com/scholar?q=Ruihong+Zeng%2C+Jinyuan+Fang%2C+Siwei+Liu%2C+and+Zaiqiao+Meng%2E+2024%2E+On+the+structural+memory+of+llm+agents%2E+arXiv+preprint+arXiv%3A2412%2E15266%2E+%E2%80%94+%5BarXiv%3A2412%2E15266%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2412%2E15266%29)
47. Wujiang Xu, Kai Mei, Hang Gao, Juntao Tan, Zujie Liang, and Yongfeng Zhang. 2025. [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.
48. Guibin Zhang, Muxin Fu, Guancheng Wan, Miao Yu, Kun Wang, and Shuicheng Yan. 2025a. G-memory: Tracing hierarchical memory for multi-agent systems. arXiv preprint arXiv:2506.07398. — [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+2025a%2E+G%2Dmemory%3A+Tracing+hierarchical+memory+for+multi%2Dagent+systems%2E+arXiv+preprint+arXiv%3A2506%2E07398%2E+%E2%80%94+%5BarXiv%3A2506%2E07398%5D)
49. Hongkang Yang, Zehao Lin, Wenjin Wang, Hao Wu, Zhiyu Li, Bo Tang, Wenqiang Wei, Jinbo Wang, Zeyun Tang, Shichao Song, and 1 others. 2024. Memory3: Language modeling with explicit memory. arXiv preprint arXiv:2407.01178. — [arXiv:2407.01178](https://arxiv.org/abs/2407.01178) [find](https://scholar.google.com/scholar?q=Hongkang+Yang%2C+Zehao+Lin%2C+Wenjin+Wang%2C+Hao+Wu%2C+Zhiyu+Li%2C+Bo+Tang%2C+Wenqiang+Wei%2C+Jinbo+Wang%2C+Zeyun+Tang%2C+Shichao+Song%2C+and+1+others%2E+2024%2E+Memory3%3A+Language+modeling+with+explicit+memory%2E+arXiv+preprin)
50. Yue Zhang, Yafu Li, Leyang Cui, Deng Cai, Lemao Liu, Tingchen Fu, Xinting Huang, Enbo Zhao, Yu Zhang, Yulong Chen, and 1 others. 2025b. [Siren’s song in the ai ocean: A survey on hallucination in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2023-siren-s-song-ai-ocean/). Computational Linguistics, pages 1–46.
51. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. [Hotpotqa: A dataset for diverse, explainable multi-hop question answering](https://md.research.elamur.ai/free/en/papers/yang-2018-hotpotqa-dataset-diverse-explainable-multi/). arXiv preprint arXiv:1809.09600.
52. Hao Zheng, Guozhao Mo, Xinru Yan, Qianhao Yuan, Wenkai Zhang, Xuanang Chen, Yaojie Lu, Hongyu Lin, Xianpei Han, and Le Sun. 2026. [Deeppresenter: Environment-grounded reflection for agentic presentation generation](https://md.research.elamur.ai/free/en/papers/zheng-2026-deeppresenter-environment-grounded-reflection-agentic/). arXiv preprint arXiv:2602.22839.
53. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. [React: Synergizing reasoning and acting in language models](https://md.research.elamur.ai/free/en/papers/yao-2022-react-synergizing-reasoning-acting-language/). In International Conference on Learning Representations (ICLR).
54. Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. 2024. Memorybank: Enhancing large language models with long-term memory. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19724–19731. [find](https://scholar.google.com/scholar?q=Wanjun+Zhong%2C+Lianghong+Guo%2C+Qiqi+Gao%2C+He+Ye%2C+and+Yanlin+Wang%2E+2024%2E+Memorybank%3A+Enhancing+large+language+models+with+long%2Dterm+memory%2E+In+Proceedings+of+the+AAAI+Conference+on+Artificial+Intelligence)
55. Hongli Yu, Tinghong Chen, Jiangtao Feng, Jiangjie Chen, Weinan Dai, Qiying Yu, Ya-Qin Zhang, Wei-Ying Ma, Jingjing Liu, Mingxuan Wang, and 1 others. 2025. Memagent: Reshaping long-context llm with multi-conv rl-based memory agent. arXiv preprint arXiv:2507.02259. — [arXiv:2507.02259](https://arxiv.org/abs/2507.02259) [find](https://scholar.google.com/scholar?q=Hongli+Yu%2C+Tinghong+Chen%2C+Jiangtao+Feng%2C+Jiangjie+Chen%2C+Weinan+Dai%2C+Qiying+Yu%2C+Ya%2DQin+Zhang%2C+Wei%2DYing+Ma%2C+Jingjing+Liu%2C+Mingxuan+Wang%2C+and+1+others%2E+2025%2E+Memagent%3A+Reshaping+long%2Dcontext+llm+with+mul)
56. Zijian Zhou, Ao Qu, Zhaoxuan Wu, Sunghwan Kim, Alok Prakash, Daniela Rus, Jinhua Zhao, Bryan Kian Hsiang Low, and Paul Pu Liang. 2025. Mem1: Learning to synergize memory and reasoning for efficient long-horizon agents. arXiv preprint arXiv:2506.15841. — [arXiv:2506.15841](https://arxiv.org/abs/2506.15841) [find](https://scholar.google.com/scholar?q=Zijian+Zhou%2C+Ao+Qu%2C+Zhaoxuan+Wu%2C+Sunghwan+Kim%2C+Alok+Prakash%2C+Daniela+Rus%2C+Jinhua+Zhao%2C+Bryan+Kian+Hsiang+Low%2C+and+Paul+Pu+Liang%2E+2025%2E+Mem1%3A+Learning+to+synergize+memory+and+reasoning+for+efficient+lo)
57. Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, and 1 others. 2023. [Ghost in the minecraft: Generally capable agents for open-world environments via large language models with text-based knowledge and memory](https://md.research.elamur.ai/free/en/papers/zhu-2023-ghost-minecraft-generally-capable-agents/). arXiv preprint arXiv:23…

*Updated 2 November 2026*