---
title: "Agent-GWO — paper by Wang et al. (2026) — summary and ideas"
description: "Reasoning quality in LLMs depends heavily on hand-written prompts and decoding settings. 73 references."
authors: ["Xudong Wang", "Chaoning Zhang", "Chenghao Li", "Shuxu Chen", "Qigan Sun", "Jiaquan Zhang", "Fachrina Dewi Puspitasari", "Tae-Ho Kim", "Jiwei Wei", "Malu Zhang", "Guoqing Wang", "Yang Yang", "Heng Tao Shen"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.821/"
doi: "10.18653/v1/2026.findings-acl.821"
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/wang-2026-agent-gwo-collaborative-agents-dynamic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-agent-gwo-collaborative-agents-dynamic/)

[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/21/) / Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models

# Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models

**Authors:** Xudong Wang, [Chaoning Zhang](https://md.research.elamur.ai/free/en/authors/chaoning-zhang/), Chenghao Li, [Shuxu Chen](https://md.research.elamur.ai/free/en/authors/shuxu-chen/), Qigan Sun, [Jiaquan Zhang](https://md.research.elamur.ai/free/en/authors/jiaquan-zhang/), Fachrina Dewi Puspitasari, Tae-Ho Kim, [Jiwei Wei](https://md.research.elamur.ai/free/en/authors/jiwei-wei/), Malu Zhang, Guoqing Wang, [Yang Yang](https://md.research.elamur.ai/free/en/authors/yang-yang/) and [Heng Tao Shen](https://md.research.elamur.ai/free/en/authors/heng-tao-shen/) · **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.821/) · [PDF](https://aclanthology.org/2026.findings-acl.821.pdf) · [DOI 10.18653/v1/2026.findings-acl.821](https://doi.org/10.18653/v1/2026.findings-acl.821) · [OpenAlex](https://openalex.org/W7166823614)

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

## Summary
Reasoning quality in LLMs depends heavily on hand-written prompts and decoding settings. Small rewordings or configuration changes can cause large accuracy swings, and earlier automatic prompt optimizers usually run a single-agent local search that adjusts only the prompt. Agent-GWO addresses this by treating each "agent" as a pairing of a reasoning prompt template with its own decoding hyperparameters, all on top of a frozen model. A population of such agents solves benchmark questions, and the agents are ranked by task accuracy. Following the Grey Wolf Optimizer, the three best agents (α, β, δ) steer how the remaining agents (ω) update their prompts and parameters. After several rounds, the top α configuration is kept and reused for inference with no further training. The method is evaluated on mathematical and mixed-reasoning benchmarks across several LLM backbones. The authors report consistently higher and more stable accuracy than manual prompting baselines and earlier prompt-optimization methods. This makes the approach a practical, training-free way to tune reasoning setups, although the search itself requires extra compute at test time.

## Key points
- **Agent definition:** each agent pairs a prompt template with five decoding hyperparameters: temperature, top-p, a cap on output length in tokens, and separate penalties based on token presence and token frequency. These are drawn from normal or uniform distributions and clipped to valid ranges.
- **Benchmarks:**
  - Math: GSM8K, MATH, SVAMP, MultiArith, ASDiv, AQUA.
  - Hybrid reasoning: MMLU, BBH, Date, CLUTRR, MATH_MIX.
- **Population size (gpt-4o-mini):** growing the population from 5 to 10 agents raised GSM8K accuracy from 95.9% to 97.5% and MMLU from 75.3% to 77.1%, with diminishing returns. Increasing iterations from 10 to 30 also helped.
- **Number of leaders:** this ablation shows an inverted-U pattern, with three leaders working best. With one leader the scores were GSM8K 92.4, MATH 76.8 and MMLU 72.0. With three leaders they rose to 95.9, 80.2 and 75.3. Adding lower-ranked agents as leaders weakened the guidance signal.
- **Robustness and limitations:** the method proved largely insensitive to moderate changes in the decoding-sampling settings. Its main limitation is the higher inference-time cost of running multiple agents over multiple iterations.

*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 (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,426 works

## Cite

Cite as: Xudong Wang, Chaoning Zhang, Chenghao Li, Shuxu Chen, Qigan Sun, Jiaquan Zhang, Fachrina Dewi Puspitasari, Tae-Ho Kim, Jiwei Wei, Malu Zhang, Guoqing Wang, Yang Yang and Heng Tao Shen. 2026. Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models. 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{wang2026agent,
  title = {{Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models}},
  author = {Xudong Wang, Chaoning Zhang, Chenghao Li, Shuxu Chen, Qigan Sun, Jiaquan Zhang, Fachrina Dewi Puspitasari, Tae-Ho Kim, Jiwei Wei, Malu Zhang, Guoqing Wang, Yang Yang and Heng Tao Shen},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.821},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.821}
}
```

- [← previous Agent Newsroom: Efficient Chronological Report Generation via Dynamic Multi-Agent Collaboration](https://md.research.elamur.ai/free/en/papers/wang-2026-agent-newsroom-efficient-chronological-report/)
- [next → Agent-Ops: A Multi-Agent Orchestration Framework for End-to-End SOP Automation in E-Commerce Operations](https://md.research.elamur.ai/free/en/papers/singh-2026-agent-ops-multi-agent-orchestration/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/21/)

## References

73 references, 29 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Nurul Fajrin Ariyani, Zied Bouraoui, Richard Booth, and Steven Schockaert. 2025. There’s no such thing as simple reasoning for llms. In Findings of the Association for Computational Linguistics: ACL 2025, pages 4503–4514. [find](https://scholar.google.com/scholar?q=Nurul+Fajrin+Ariyani%2C+Zied+Bouraoui%2C+Richard+Booth%2C+and+Steven+Schockaert%2E+2025%2E+There%E2%80%99s+no+such+thing+as+simple+reasoning+for+llms%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2)
2. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and 1 others. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI conference on a… [find](https://scholar.google.com/scholar?q=Maciej+Besta%2C+Nils+Blach%2C+Ales+Kubicek%2C+Robert+Gerstenberger%2C+Michal+Podstawski%2C+Lukas+Gianinazzi%2C+Joanna+Gajda%2C+Tomasz+Lehmann%2C+Hubert+Niewiadomski%2C+Piotr+Nyczyk%2C+and+1+others%2E+2024%2E+Graph+of+thought)
3. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in neural information processing systems, 33:1877–1901.
4. Bowen Cao, Deng Cai, Zhisong Zhang, Yuexian Zou, and Wai Lam. 2024. On the worst prompt performance of large language models. Advances in Neural Information Processing Systems, 37:69022–69042. [find](https://scholar.google.com/scholar?q=Bowen+Cao%2C+Deng+Cai%2C+Zhisong+Zhang%2C+Yuexian+Zou%2C+and+Wai+Lam%2E+2024%2E+On+the+worst+prompt+performance+of+large+language+models%2E+Advances+in+Neural+Information+Processing+Systems%2C+37%3A69022%E2%80%9369042%2E)
5. Sihan Cao, Jianwei Zhang, Pengcheng Zheng, Jiaxin Yan, Caiyan Qin, Yalan Ye, Wei Dong, Peng Wang, Yang Yang, and Chaoning Zhang. 2026. Language-guided token compression with reinforcement learning in large vision-language models. arXiv preprint arXiv:2603.13394. — [arXiv:2603.13394](https://arxiv.org/abs/2603.13394) [find](https://scholar.google.com/scholar?q=Sihan+Cao%2C+Jianwei+Zhang%2C+Pengcheng+Zheng%2C+Jiaxin+Yan%2C+Caiyan+Qin%2C+Yalan+Ye%2C+Wei+Dong%2C+Peng+Wang%2C+Yang+Yang%2C+and+Chaoning+Zhang%2E+2026%2E+Language%2Dguided+token+compression+with+reinforcement+learning+in+)
6. Anwoy Chatterjee, HSVNS Kowndinya Renduchintala, Sumit Bhatia, and Tanmoy Chakraborty. 2024. Posix: A prompt sensitivity index for large language models. arXiv preprint arXiv:2410.02185. [find](https://scholar.google.com/scholar?q=Anwoy+Chatterjee%2C+HSVNS+Kowndinya+Renduchintala%2C+Sumit+Bhatia%2C+and+Tanmoy+Chakraborty%2E+2024%2E+Posix%3A+A+prompt+sensitivity+index+for+large+language+models%2E+arXiv+preprint+arXiv%3A2410%2E02185%2E)
7. Xinyun Chen, Jacob Tworek, Heewoo Jun, Qiming Yuan, Maarten Bosma, Yi Luan, Denny Zhou, Quoc V Le, and Luke Zettlemoyer. 2022. Program-of-thoughts prompting: Disentangling computation from reasoning for numerical reasoning tasks. In Advances in Neural Information Processing Systems, volume 35, pages… [find](https://scholar.google.com/scholar?q=Xinyun+Chen%2C+Jacob+Tworek%2C+Heewoo+Jun%2C+Qiming+Yuan%2C+Maarten+Bosma%2C+Yi+Luan%2C+Denny+Zhou%2C+Quoc+V+Le%2C+and+Luke+Zettlemoyer%2E+2022%2E+Program%2Dof%2Dthoughts+prompting%3A+Disentangling+computation+from+reasoning+f)
8. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, and 1 others. 2021. [Training verifiers to solve math word problems](https://md.research.elamur.ai/free/en/papers/cobbe-2021-training-verifiers-solve-math-word/). arXiv preprint arXiv:2110.14168.
9. Yilun Du, Shuang Li, Antonio Torralba, Joshua B Tenenbaum, and Igor Mordatch. 2023. [Improving factuality and reasoning in language models through multiagent debate](https://md.research.elamur.ai/free/en/papers/du-2023-improving-factuality-reasoning-language-models/). In Forty-first International Conference on Machine Learning.
10. Jacques Ferber and Gerhard Weiss. 1999. Multi-agent systems: an introduction to distributed artificial intelligence, volume 1. Addison-wesley Reading. [find](https://scholar.google.com/scholar?q=Jacques+Ferber+and+Gerhard+Weiss%2E+1999%2E+Multi%2Dagent+systems%3A+an+introduction+to+distributed+artificial+intelligence%2C+volume+1%2E+Addison%2Dwesley+Reading%2E)
11. Ferdinando Fioretto, Enrico Pontelli, and William Yeoh. 2018. Distributed constraint optimization problems and applications: A survey. Journal of Artificial Intelligence Research, 61:623–698. [find](https://scholar.google.com/scholar?q=Ferdinando+Fioretto%2C+Enrico+Pontelli%2C+and+William+Yeoh%2E+2018%2E+Distributed+constraint+optimization+problems+and+applications%3A+A+survey%2E+Journal+of+Artificial+Intelligence+Research%2C+61%3A623%E2%80%93698%2E)
12. ACL Fipa. 2002. Fipa acl message structure specification. Foundation for Intelligent Physical Agents, [http://www.fipa](http://www.fipa). org/specs/fipa00061/SC00061G. html (30.6. 2004). [↗](http://www.fipa)
13. Yancheng He, Shilong Li, Jiaheng Liu, Weixun Wang, Xingyuan Bu, Ge Zhang, Zy Peng, Zhaoxiang Zhang, Zhicheng Zheng, Wenbo Su, and 1 others. 2025. [Can large language models detect errors in long chain-of-thought reasoning?](https://md.research.elamur.ai/free/en/papers/he-2025-can-large-language-models-detect/) In Proceedings of the 63rd Annual Meeting of the Association for Computational…
14. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. [Measuring mathematical problem solving with the math dataset](https://md.research.elamur.ai/free/en/papers/hendrycks-2021-measuring-mathematical-problem-solving-math/). arXiv preprint arXiv:2103.03874.
15. Sirui Hong, Yizhang Lin, Bang Liu, Bangbang Liu, Binhao Wu, Ceyao Zhang, Danyang Li, Jiaqi Chen, Jiayi Zhang, Jinlin Wang, and 1 others. 2025. [Data interpreter: An llm agent for data science](https://md.research.elamur.ai/free/en/papers/hong-2025-data-interpreter-llm-agent-data/). In Findings of the Association for Computational Linguistics: ACL 2025, pages 19796–19821.
16. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, and 1 others. 2022. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). ICLR, 1(2):3.
17. Shengran Hu, Cong Lu, and Jeff Clune. 2024. Automated design of agentic systems. arXiv preprint arXiv:2408.08435. [find](https://scholar.google.com/scholar?q=Shengran+Hu%2C+Cong+Lu%2C+and+Jeff+Clune%2E+2024%2E+Automated+design+of+agentic+systems%2E+arXiv+preprint+arXiv%3A2408%2E08435%2E)
18. Fanding Huang, Guanbo Huang, Xiao Fan, Yi He, Xiao Liang, Xiao Chen, Qinting Jiang, Faisal Nadeem Khan, Jingyan Jiang, and Zhi Wang. 2026. Semantic-space exploration and exploitation in rlvr for llm reasoning. Preprint, arXiv:2509.23808. [find](https://scholar.google.com/scholar?q=Fanding+Huang%2C+Guanbo+Huang%2C+Xiao+Fan%2C+Yi+He%2C+Xiao+Liang%2C+Xiao+Chen%2C+Qinting+Jiang%2C+Faisal+Nadeem+Khan%2C+Jingyan+Jiang%2C+and+Zhi+Wang%2E+2026%2E+Semantic%2Dspace+exploration+and+exploitation+in+rlvr+for+llm+r)
19. Shima Imani, Liang Du, and Harsh Shrivastava. 2023. [Mathprompter: Mathematical reasoning using large language models](https://md.research.elamur.ai/free/en/papers/imani-2023-mathprompter-mathematical-reasoning-large-language/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 37–42.
20. Jiechuan Jiang and Zongqing Lu. 2018. Learning attentional communication for multi-agent cooperation. Advances in neural information processing systems, 31. [find](https://scholar.google.com/scholar?q=Jiechuan+Jiang+and+Zongqing+Lu%2E+2018%2E+Learning+attentional+communication+for+multi%2Dagent+cooperation%2E+Advances+in+neural+information+processing+systems%2C+31%2E)
21. Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, and Mengnan Du. 2024. [The impact of reasoning step length on large language models](https://md.research.elamur.ai/free/en/papers/jin-2024-impact-reasoning-step-length-large/). arXiv preprint arXiv:2401.04925.
22. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). Advances in neural information processing systems, 35:22199– 22213.
23. Xinyun Lu, Xiujun Li, Di He, Jianfeng Gao, and Li Deng. 2022. Fantastically ordered prompts and where to find them. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, volume 1, pages 8000–8011. [find](https://scholar.google.com/scholar?q=Xinyun+Lu%2C+Xiujun+Li%2C+Di+He%2C+Jianfeng+Gao%2C+and+Li+Deng%2E+2022%2E+Fantastically+ordered+prompts+and+where+to+find+them%2E+In+Proceedings+of+the+60th+Annual+Meeting+of+the+Association+for+Computational+Lingu)
24. Pranjal Kumar. 2024. Large language models (llms): survey, technical frameworks, and future challenges. Artificial Intelligence Review, 57(10):260. [find](https://scholar.google.com/scholar?q=Pranjal+Kumar%2E+2024%2E+Large+language+models+%28llms%29%3A+survey%2C+technical+frameworks%2C+and+future+challenges%2E+Artificial+Intelligence+Review%2C+57%2810%29%3A260%2E)
25. Qing Lyu, Shreya Havaldar, Adam Stein, Li Zhang, Delip Rao, Eric Wong, Marianna Apidianaki, and Chris Callison-Burch. 2023. [Faithful chain-of-thought reasoning](https://md.research.elamur.ai/free/en/papers/lyu-2023-faithful-chain-thought-reasoning/). In The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Associa…
26. Joshua Ong Jun Leang, Aryo Pradipta Gema, and Shay B Cohen. 2025. [Comat: Chain of mathematically annotated thought improves mathematical reasoning](https://md.research.elamur.ai/free/en/papers/leang-2025-comat-chain-mathematically-annotated-thought/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 20256–20285.
27. Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. [The power of scale for parameter-efficient prompt tuning](https://md.research.elamur.ai/free/en/papers/lester-2021-power-scale-parameter-efficient-prompt/). arXiv preprint arXiv:2104.08691.
28. Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, and 1 others. 2023. Self-refine: Iterative refinement with self-feedback. Advances in Neural Information Processing Systems, 36:46534–46594. [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+and+1+others%2E+2023%2E+Self%2Drefine%3A+Iterative+refinement+with)
29. Chunyang Li, Weiqi Wang, Tianshi Zheng, and Yangqiu Song. 2025a. Patterns over principles: The fragility of inductive reasoning in llms under noisy observations. arXiv preprint arXiv:2502.16169. [find](https://scholar.google.com/scholar?q=Chunyang+Li%2C+Weiqi+Wang%2C+Tianshi+Zheng%2C+and+Yangqiu+Song%2E+2025a%2E+Patterns+over+principles%3A+The+fragility+of+inductive+reasoning+in+llms+under+noisy+observations%2E+arXiv+preprint+arXiv%3A2502%2E16169%2E)
30. Mohammad Reza Ghasemi Madani, Soyeon Caren Han, Shuo Yang, and Jey Han Lau. 2026. Inclusion-of-thoughts: Mitigating preference instability via purifying the decision space. arXiv preprint arXiv:2604.04944. — [arXiv:2604.04944](https://arxiv.org/abs/2604.04944) [find](https://scholar.google.com/scholar?q=Mohammad+Reza+Ghasemi+Madani%2C+Soyeon+Caren+Han%2C+Shuo+Yang%2C+and+Jey+Han+Lau%2E+2026%2E+Inclusion%2Dof%2Dthoughts%3A+Mitigating+preference+instability+via+purifying+the+decision+space%2E+arXiv+preprint+arXiv%3A2604%2E0)
31. Junlong Li, Daya Guo, Dejian Yang, Runxin Xu, Yu Wu, and Junxian He. 2025b. [Codei/o: Condensing reasoning patterns via code input-output prediction](https://md.research.elamur.ai/free/en/papers/li-2025-codei-o-condensing-reasoning/). arXiv preprint arXiv:2502.07316.
32. Shen-Yun Miao, Chao-Chun Liang, and Keh-Yih Su. 2020. A diverse corpus for evaluating and developing english math word problem solvers. In Proceedings of the 58th annual meeting of the Association for Computational Linguistics, pages 975–984. [find](https://scholar.google.com/scholar?q=Shen%2DYun+Miao%2C+Chao%2DChun+Liang%2C+and+Keh%2DYih+Su%2E+2020%2E+A+diverse+corpus+for+evaluating+and+developing+english+math+word+problem+solvers%2E+In+Proceedings+of+the+58th+annual+meeting+of+the+Association+for)
33. Nian Li, Chen Gao, Mingyu Li, Yong Li, and Qingmin Liao. 2023. [Econagent: large language model-empowered agents for simulating macroeconomic activities](https://md.research.elamur.ai/free/en/papers/li-2024-econagent-large-language-model-empowered/). arXiv preprint arXiv:2310.10436.
34. Jonghan Lim, Birgit Vogel-Heuser, and Ilya Kovalenko. 2024. Large language model-enabled multi-agent manufacturing systems. In 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE), pages 3940–3946. IEEE. [find](https://scholar.google.com/scholar?q=Jonghan+Lim%2C+Birgit+Vogel%2DHeuser%2C+and+Ilya+Kovalenko%2E+2024%2E+Large+language+model%2Denabled+multi%2Dagent+manufacturing+systems%2E+In+2024+IEEE+20th+International+Conference+on+Automation+Science+and+Enginee)
35. Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. 2017. Program induction by rationale generation: Learning to solve and explain algebraic word problems. [https://github.com/](https://github.com/) google-deepmind/AQuA. NeurIPS Datasets Track Reference. [↗](https://github.com/)
36. Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, and 1 others. 2025. Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary, collaborative, and safe systems. arXiv preprint arXiv:2504… — [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+and+1+others%2E+2025%2E+Advances+and+challenges+in+foundation+agents%3A+From+bra)
37. Yujun Liu, Xinyun Chen, Jacob Tworek, Qiming Yuan, Maarten Bosma, Yi Luan, Denny Zhou, Quoc V Le, and Luke Zettlemoyer. 2023. Graph-of-thought prompting: Structuring reasoning as dependency graphs. In Advances in Neural Information Processing Systems, volume 36, pages 10243–10257. [find](https://scholar.google.com/scholar?q=Yujun+Liu%2C+Xinyun+Chen%2C+Jacob+Tworek%2C+Qiming+Yuan%2C+Maarten+Bosma%2C+Yi+Luan%2C+Denny+Zhou%2C+Quoc+V+Le%2C+and+Luke+Zettlemoyer%2E+2023%2E+Graph%2Dof%2Dthought+prompting%3A+Structuring+reasoning+as+dependency+graphs%2E+In)
38. Seyedali Mirjalili, Seyed Mohammad Mirjalili, and Andrew Lewis. 2014. Grey wolf optimizer. Advances in engineering software, 69:46–61. [find](https://scholar.google.com/scholar?q=Seyedali+Mirjalili%2C+Seyed+Mohammad+Mirjalili%2C+and+Andrew+Lewis%2E+2014%2E+Grey+wolf+optimizer%2E+Advances+in+engineering+software%2C+69%3A46%E2%80%9361%2E)
39. Humza Naveed, Asad Ullah Khan, Shi Qiu, Muhammad Saqib, Saeed Anwar, Muhammad Usman, Naveed Akhtar, Nick Barnes, and Ajmal Mian. 2023. [A comprehensive overview of large language models](https://md.research.elamur.ai/free/en/papers/naveed-2023-comprehensive-overview-large-language-models/). arXiv preprint arXiv:2307.06435.
40. Joon Sung Park, Joseph O’Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. 2023. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22. [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+2023%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+In+Proceedings+of+the+36)
41. Arkil Patel, Satwik Bhattamishra, and Navin Goyal. 2021. [Are nlp models really able to solve simple math word problems?](https://md.research.elamur.ai/free/en/papers/patel-2021-are-nlp-models-really-able/) In Proceedings of the 2021 conference of the North American chapter of the association for computational linguistics: human language technologies, pages 2080–2094.
42. Ofir Press, Mike Lewis Lee, and Luke Zettlemoyer. 2022. Self-ask with search: Bootstrapping reasoning with chain-of-thought. In Advances in Neural Information Processing Systems, volume 35, pages 24804–24817. [find](https://scholar.google.com/scholar?q=Ofir+Press%2C+Mike+Lewis+Lee%2C+and+Luke+Zettlemoyer%2E+2022%2E+Self%2Dask+with+search%3A+Bootstrapping+reasoning+with+chain%2Dof%2Dthought%2E+In+Advances+in+Neural+Information+Processing+Systems%2C+volume+35%2C+pages+2480)
43. Alec Radford, Karthik Narasimhan, Tim Salimans, Ilya Sutskever, and 1 others. 2018. Improving language understanding by generative pre-training. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Karthik+Narasimhan%2C+Tim+Salimans%2C+Ilya+Sutskever%2C+and+1+others%2E+2018%2E+Improving+language+understanding+by+generative+pre%2Dtraining%2E)
44. Subhro Roy and Dan Roth. 2015. [Solving general arithmetic word problems](https://md.research.elamur.ai/free/en/papers/roy-2015-solving-general-arithmetic-word-problems/). In Proceedings of the 2015 conference on empirical methods in natural language processing, pages 1743–1752.
45. Jon Saad-Falcon, Adrian Gamarra Lafuente, Shlok Natarajan, Nahum Maru, Hristo Todorov, Etash Guha, E Kelly Buchanan, Mayee Chen, Neel Guha, Christopher Ré, and 1 others. 2024. Archon: An architecture search framework for inference-time techniques. arXiv preprint arXiv:2409.15254. — [arXiv:2409.15254](https://arxiv.org/abs/2409.15254) [find](https://scholar.google.com/scholar?q=Jon+Saad%2DFalcon%2C+Adrian+Gamarra+Lafuente%2C+Shlok+Natarajan%2C+Nahum+Maru%2C+Hristo+Todorov%2C+Etash+Guha%2C+E+Kelly+Buchanan%2C+Mayee+Chen%2C+Neel+Guha%2C+Christopher+R%C3%A9%2C+and+1+others%2E+2024%2E+Archon%3A+An+architecture+)
46. Koustuv Sinha, Shagun Sodhani, Jin Dong, Joelle Pineau, and William L Hamilton. 2019. Clutrr: A diagnostic benchmark for inductive reasoning from text. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Lang… [find](https://scholar.google.com/scholar?q=Koustuv+Sinha%2C+Shagun+Sodhani%2C+Jin+Dong%2C+Joelle+Pineau%2C+and+William+L+Hamilton%2E+2019%2E+Clutrr%3A+A+diagnostic+benchmark+for+inductive+reasoning+from+text%2E+In+Proceedings+of+the+2019+Conference+on+Empiric)
47. Saksham Sahai Srivastava and Ashutosh Gandhi. 2024. Mathdivide: Improved mathematical reasoning by large language models. arXiv preprint arXiv:2405.13004. — [arXiv:2405.13004](https://arxiv.org/abs/2405.13004) [find](https://scholar.google.com/scholar?q=Saksham+Sahai+Srivastava+and+Ashutosh+Gandhi%2E+2024%2E+Mathdivide%3A+Improved+mathematical+reasoning+by+large+language+models%2E+arXiv+preprint+arXiv%3A2405%2E13004%2E+%E2%80%94+%5BarXiv%3A2405%2E13004%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F24)
48. Mirac Suzgun, Nathan Scales, Nathanael Schärli, Sebastian Gehrmann, Yi Tay, Hyung Won Chung, Aakanksha Chowdhery, Quoc Le, Ed Chi, Denny Zhou, and 1 others. 2023. [Challenging big-bench tasks and whether chain-of-thought can solve them](https://md.research.elamur.ai/free/en/papers/suzgun-2023-challenging-big-bench-tasks-whether/). In Findings of the Association for Computational Linguistics: AC…
49. Fengwei Teng, Zhaoyang Yu, Quan Shi, Jiayi Zhang, Chenglin Wu, and Yuyu Luo. 2025. Atom of thoughts for markov llm test-time scaling. arXiv preprint arXiv:2502.12018. — [arXiv:2502.12018](https://arxiv.org/abs/2502.12018) [find](https://scholar.google.com/scholar?q=Fengwei+Teng%2C+Zhaoyang+Yu%2C+Quan+Shi%2C+Jiayi+Zhang%2C+Chenglin+Wu%2C+and+Yuyu+Luo%2E+2025%2E+Atom+of+thoughts+for+markov+llm+test%2Dtime+scaling%2E+arXiv+preprint+arXiv%3A2502%2E12018%2E+%E2%80%94+%5BarXiv%3A2502%2E12018%5D%28https%3A%2F%2Farxi)
50. Chengbing Wang, Yang Zhang, Wenjie Wang, Xiaoyan Zhao, Fuli Feng, Xiangnan He, and Tat-Seng Chua. 2025. Think-while-generating: On-the-fly reasoning for personalized long-form generation. arXiv preprint arXiv:2512.06690. — [arXiv:2512.06690](https://arxiv.org/abs/2512.06690) [find](https://scholar.google.com/scholar?q=Chengbing+Wang%2C+Yang+Zhang%2C+Wenjie+Wang%2C+Xiaoyan+Zhao%2C+Fuli+Feng%2C+Xiangnan+He%2C+and+Tat%2DSeng+Chua%2E+2025%2E+Think%2Dwhile%2Dgenerating%3A+On%2Dthe%2Dfly+reasoning+for+personalized+long%2Dform+generation%2E+arXiv+prepri)
51. Junxi Wang, Te Sun, Jiayi Zhu, Junxian Li, Haowen Xu, Zichen Wen, Xuming Hu, Zhiyu Li, and Linfeng Zhang. 2026. [Streammeco: Long-term agent memory compression for efficient streaming video understanding](https://md.research.elamur.ai/free/en/papers/wang-2026-streammeco-long-term-agent-memory/). Preprint, arXiv:2604.09000.
52. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. [Self-consistency improves chain of thought reasoning in language models](https://md.research.elamur.ai/free/en/papers/wang-2022-self-consistency-improves-chain-thought/). arXiv preprint arXiv:2203.11171.
53. 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.
54. Michael Wooldridge and Nicholas R Jennings. 1995. Intelligent agents: Theory and practice. The knowledge engineering review, 10(2):115–152. [find](https://scholar.google.com/scholar?q=Michael+Wooldridge+and+Nicholas+R+Jennings%2E+1995%2E+Intelligent+agents%3A+Theory+and+practice%2E+The+knowledge+engineering+review%2C+10%282%29%3A115%E2%80%93152%2E)
55. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, and 1 others. 2023. [Autogen: Enabling next-gen llm applications via multi-agent conversation](https://md.research.elamur.ai/free/en/papers/wu-2023-autogen-enabling-next-gen-llm/). arXiv preprint arXiv:2308.08155.
56. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, and 1 others. 2025. [The rise and potential of large language model based agents: A survey](https://md.research.elamur.ai/free/en/papers/xi-2023-rise-potential-large-language/). Science China Information Sciences, 68(2):121101.
57. Shijia Xu, Yu Wang, Xiaolong Jia, Zhou Wu, Kai Liu, and April Xiaowen Dong. 2026. [Rcbsf: A multi-agent framework for automated contract revision via stackelberg game](https://md.research.elamur.ai/free/en/papers/xu-2026-rcbsf-multi-agent-framework-automated/). Preprint, arXiv:2604.10740.
58. Shuo Yang, Soyeon Caren Han, Yihao Ding, Shuhe Wang, and Eduard Hoy. 2026a. Tooltree: Efficient llm agent tool planning via dual-feedback monte carlo tree search and bidirectional pruning. arXiv preprint arXiv:2603.12740. — [arXiv:2603.12740](https://arxiv.org/abs/2603.12740) [find](https://scholar.google.com/scholar?q=Shuo+Yang%2C+Soyeon+Caren+Han%2C+Yihao+Ding%2C+Shuhe+Wang%2C+and+Eduard+Hoy%2E+2026a%2E+Tooltree%3A+Efficient+llm+agent+tool+planning+via+dual%2Dfeedback+monte+carlo+tree+search+and+bidirectional+pruning%2E+arXiv+prepr)
59. Shuo Yang, Soyeon Caren Han, Xueqi Ma, Yan Li, Mohammad Reza Ghasemi Madani, and Eduard Hovy. 2026b. [Evotool: Self-evolving tool-use policy optimization in llm agents via blame-aware mutation and diversity-aware selection](https://md.research.elamur.ai/free/en/papers/yang-2026-evotool-self-evolving-tool-use/). arXiv preprint arXiv:2603.04900.
60. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, 36:11809–11822. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+2023%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Advances+in+neural+inf)
61. Murong Yue, Jie Zhao, Min Zhang, Liang Du, and Ziyu Yao. 2023. Large language model cascades with mixture of thoughts representations for cost-efficient reasoning. arXiv preprint arXiv:2310.03094. — [arXiv:2310.03094](https://arxiv.org/abs/2310.03094) [find](https://scholar.google.com/scholar?q=Murong+Yue%2C+Jie+Zhao%2C+Min+Zhang%2C+Liang+Du%2C+and+Ziyu+Yao%2E+2023%2E+Large+language+model+cascades+with+mixture+of+thoughts+representations+for+cost%2Defficient+reasoning%2E+arXiv+preprint+arXiv%3A2310%2E03094%2E+%E2%80%94+%5B)
62. An Zhang, Yuxin Chen, Leheng Sheng, Xiang Wang, and Tat-Seng Chua. 2024a. On generative agents in recommendation. In Proceedings of the 47th international ACM SIGIR conference on research and development in Information Retrieval, pages 1807– 1817. [find](https://scholar.google.com/scholar?q=An+Zhang%2C+Yuxin+Chen%2C+Leheng+Sheng%2C+Xiang+Wang%2C+and+Tat%2DSeng+Chua%2E+2024a%2E+On+generative+agents+in+recommendation%2E+In+Proceedings+of+the+47th+international+ACM+SIGIR+conference+on+research+and+developm)
63. Jiaquan Zhang, Qigan Sun, Chaoning Zhang, Xudong Wang, Zhenzhen Huang, Yitian Zhou, Pengcheng Zheng, Chi-lok Andy Tai, Sung-Ho Bae, Zeyu Ma, and 1 others. 2026a. Tda-rc: Task-driven alignment for knowledge-based reasoning chains in large language models. arXiv preprint arXiv:2604.04942. — [arXiv:2604.04942](https://arxiv.org/abs/2604.04942) [find](https://scholar.google.com/scholar?q=Jiaquan+Zhang%2C+Qigan+Sun%2C+Chaoning+Zhang%2C+Xudong+Wang%2C+Zhenzhen+Huang%2C+Yitian+Zhou%2C+Pengcheng+Zheng%2C+Chi%2Dlok+Andy+Tai%2C+Sung%2DHo+Bae%2C+Zeyu+Ma%2C+and+1+others%2E+2026a%2E+Tda%2Drc%3A+Task%2Ddriven+alignment+for+know)
64. Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Zhenzhen Huang, Pengcheng Zheng, Zhicheng Wang, Ping Guo, Fan Mo, Sung-Ho Bae, Jie Zou, Jiwei Wei, and Yang Yang. 2026b. [Lightweight llm agent memory with small language models](https://md.research.elamur.ai/free/en/papers/zhang-2026-lightweight-llm-agent-memory-small/). Preprint, arXiv:2604.07798.
65. Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Yibei Liu, Chenghao Li, Qigan Sun, Shuai Yuan, Fachrina Dewi Puspitasari, Dongshen Han, Guoqing Wang, and 1 others. 2026c. Text summarization via global structure awareness. arXiv preprint arXiv:2602.09821. — [arXiv:2602.09821](https://arxiv.org/abs/2602.09821) [find](https://scholar.google.com/scholar?q=Jiaquan+Zhang%2C+Chaoning+Zhang%2C+Shuxu+Chen%2C+Yibei+Liu%2C+Chenghao+Li%2C+Qigan+Sun%2C+Shuai+Yuan%2C+Fachrina+Dewi+Puspitasari%2C+Dongshen+Han%2C+Guoqing+Wang%2C+and+1+others%2E+2026c%2E+Text+summarization+via+global+stru)
66. Jiaquan Zhang, Chaoning Zhang, Shuxu Chen, Xudong Wang, Zhenzhen Huang, Pengcheng Zheng, Shuai Yuan, Sheng Zheng, Qigan Sun, Jie Zou, and 1 others. 2026d. Learning global hypothesis space for enhancing synergistic reasoning chain. arXiv preprint arXiv:2602.09794. — [arXiv:2602.09794](https://arxiv.org/abs/2602.09794) [find](https://scholar.google.com/scholar?q=Jiaquan+Zhang%2C+Chaoning+Zhang%2C+Shuxu+Chen%2C+Xudong+Wang%2C+Zhenzhen+Huang%2C+Pengcheng+Zheng%2C+Shuai+Yuan%2C+Sheng+Zheng%2C+Qigan+Sun%2C+Jie+Zou%2C+and+1+others%2E+2026d%2E+Learning+global+hypothesis+space+for+enhancin)
67. Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xionghui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, and 1 others. 2024b. Aflow: Automating agentic workflow generation. arXiv preprint arXiv:2410.10762. [find](https://scholar.google.com/scholar?q=Jiayi+Zhang%2C+Jinyu+Xiang%2C+Zhaoyang+Yu%2C+Fengwei+Teng%2C+Xionghui+Chen%2C+Jiaqi+Chen%2C+Mingchen+Zhuge%2C+Xin+Cheng%2C+Sirui+Hong%2C+Jinlin+Wang%2C+and+1+others%2E+2024b%2E+Aflow%3A+Automating+agentic+workflow+generation%2E+)
68. Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang, and Sercan Arik. 2024c. Chain of agents: Large language models collaborating on long-context tasks. Advances in Neural Information Processing Systems, 37:132208–132237. [find](https://scholar.google.com/scholar?q=Yusen+Zhang%2C+Ruoxi+Sun%2C+Yanfei+Chen%2C+Tomas+Pfister%2C+Rui+Zhang%2C+and+Sercan+Arik%2E+2024c%2E+Chain+of+agents%3A+Large+language+models+collaborating+on+long%2Dcontext+tasks%2E+Advances+in+Neural+Information+Proces)
69. Zhuosheng Zhang, Aston Zhang, Mu Li, and Alex Smola. 2022. [Automatic chain of thought prompting in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2022-automatic-chain-thought-prompting-large/). arXiv preprint arXiv:2210.03493.
70. Pengcheng Zheng, Xiaorong Pu, Kecheng Chen, Jiaxin Huang, Meng Yang, Bai Feng, Yazhou Ren, Jianan Jiang, Chaoning Zhang, Yang Yang, and 1 others. 2025. Joint lossless compression and steganography for medical images via large language models. arXiv preprint arXiv:2508.01782. — [arXiv:2508.01782](https://arxiv.org/abs/2508.01782) [find](https://scholar.google.com/scholar?q=Pengcheng+Zheng%2C+Xiaorong+Pu%2C+Kecheng+Chen%2C+Jiaxin+Huang%2C+Meng+Yang%2C+Bai+Feng%2C+Yazhou+Ren%2C+Jianan+Jiang%2C+Chaoning+Zhang%2C+Yang+Yang%2C+and+1+others%2E+2025%2E+Joint+lossless+compression+and+steganography+for)
71. Pengcheng Zheng, Chaoning Zhang, Mingzheng Cui, Guo Chen, Qigan Sun, Jiaxin Huang, Jiaquan Zhang, Tae-Ho Kim, Caiyan Qin, Yazhou Ren, and 1 others. 2026a. Towards visual chain-of-thought reasoning: A comprehensive survey. [find](https://scholar.google.com/scholar?q=Pengcheng+Zheng%2C+Chaoning+Zhang%2C+Mingzheng+Cui%2C+Guo+Chen%2C+Qigan+Sun%2C+Jiaxin+Huang%2C+Jiaquan+Zhang%2C+Tae%2DHo+Kim%2C+Caiyan+Qin%2C+Yazhou+Ren%2C+and+1+others%2E+2026a%2E+Towards+visual+chain%2Dof%2Dthought+reasoning%3A+A+)
72. Pengcheng Zheng, Chaoning Zhang, Jiarong Mo, Guo-Hui Li, Jiaquan Zhang, Jiahao Zhang, Sihan Cao, Sheng Zheng, Caiyan Qin, Guoqing Wang, and 1 others. 2026b. Llava-fa: Learning fourier approximation for compressing large multimodal models. arXiv preprint arXiv:2602.00135. — [arXiv:2602.00135](https://arxiv.org/abs/2602.00135) [find](https://scholar.google.com/scholar?q=Pengcheng+Zheng%2C+Chaoning+Zhang%2C+Jiarong+Mo%2C+Guo%2DHui+Li%2C+Jiaquan+Zhang%2C+Jiahao+Zhang%2C+Sihan+Cao%2C+Sheng+Zheng%2C+Caiyan+Qin%2C+Guoqing+Wang%2C+and+1+others%2E+2026b%2E+Llava%2Dfa%3A+Learning+fourier+approximation+fo)
73. Denny Zhou, Dale Schuurmans, Quoc V Le, Ed H Chi, and Jason Wei. 2022. [Least-to-most prompting enables complex reasoning in large language models](https://md.research.elamur.ai/free/en/papers/al-2022-least-most-prompting-enables-complex/). In Advances in Neural Information Processing Systems, volume 35, pages 24770–24782.

*Updated 1 November 2026*