---
title: "NeuralFSM — paper by Wang et al. (2026) — summary and ideas"
description: "It offers a single learned alternative to manually designed coordination protocols. 62 references."
authors: ["Jiye Wang", "Yu Wang", "Jianbin Li", "Shiduo Yang", "Kenan Guo", "Yuanhe Zhao"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.1543/"
doi: "10.18653/v1/2026.acl-long.1543"
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-neuralfsm-adaptive-multi-agent-coordination/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-neuralfsm-adaptive-multi-agent-coordination/)

[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/37/) / NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy

# NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy

**Authors:** Jiye Wang, [Yu Wang](https://md.research.elamur.ai/free/en/authors/yu-wang/), Jianbin Li, Shiduo Yang, Kenan Guo and Yuanhe Zhao · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/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.acl-long.1543/) · [PDF](https://aclanthology.org/2026.acl-long.1543.pdf) · [DOI 10.18653/v1/2026.acl-long.1543](https://doi.org/10.18653/v1/2026.acl-long.1543) · [OpenAlex](https://openalex.org/W7166796391)

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

## Summary
Multi-agent systems built on LLMs usually coordinate through fixed, hand-written communication schemes or through topologies searched for a particular task. These schemes transfer poorly to new tasks, waste tokens on broadcast messaging, and degrade when some agents are noisy or malicious. NeuralFSM addresses this by treating problem solving as a walk through a reusable finite state machine, where each state is handled by a responsible agent. A Temporal Coordination Controller, based on Temporal Graph Networks, reads the problem embedding and the accumulated execution history. At every step it predicts two things: which state to visit next, and a small set of agents that should receive the current output. Training maximizes task reward minus a weighted execution cost. For security, the authors add graph regularization during training and trust-based down-weighting of suspicious messages at inference. On six benchmarks the method outperforms earlier baselines on average while using fewer tokens, and it stays accurate under attack. It offers a single learned alternative to manually designed coordination protocols.

## Key points
- Across six benchmarks, NeuralFSM beats previous baselines by an average margin of 6.74%–19.39% and lowers token consumption through sparse routing.
- The controller uses Temporal Graph Networks (TGN) with GRU memory and attention-based message aggregation. MLP predictors output the state-transition distribution and the communication weights, with at most k receivers per step.
- The robustness study on GSM8K covers frequency attacks (high-rate message injection) and semantic attacks (misleading content). Under attack, relative accuracy drops are:
  - DyLAN: 17.11%
  - MaAS: 26.47%
  - MasHost: 18.60%
  - NeuralFSM without protection: 9.31%
  - NeuralFSM with the dual-defense layer: 1.82%
- A HotpotQA case study shows the model skipping states it does not need, such as a consistency check. It also re-invokes retrieval after resolving an alias, rather than following a fixed pipeline.
- The authors acknowledge several limitations: results are sensitive to hyperparameters and to how many interaction traces are available, and the benchmarks are relatively easy for modern LLMs. Code is available at github.com/DisseverYOLO/NeuralFSM.

*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

- [State Grid Corporation of China](https://md.research.elamur.ai/free/en/companies/state-grid-corporation-of-china/) — Company, Beijing, China · 2 works · 23 citations
- [North China Electric Power University](https://md.research.elamur.ai/free/en/universities/north-china-electric-power-university/) — University, Beijing, China · 3 works · 1 citation

📚 Shelves (3): [🖥️ 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 · [🌐 Computer Networks and Communications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · 64 works

## Cite

Cite as: Jiye Wang, Yu Wang, Jianbin Li, Shiduo Yang, Kenan Guo and Yuanhe Zhao. 2026. NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

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

```bibtex
@inproceedings{wang2026neuralfsm,
  title = {{NeuralFSM: Adaptive Multi-Agent Coordination via Learning Finite-State Execution Policy}},
  author = {Jiye Wang, Yu Wang, Jianbin Li, Shiduo Yang, Kenan Guo and Yuanhe Zhao},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.1543},
  url = {https://doi.org/10.18653/v1/2026.acl-long.1543}
}
```

- [← previous Neural Wani: Toward Accelerating the Automated Theorem Prover wani for Dependent Type Theory](https://md.research.elamur.ai/free/en/papers/miyagawa-2026-neural-wani-accelerating-automated-theorem/)
- [next → Neuro-symbolic Approaches for Rubric-Based Automatic Essay Evaluation of ENEM Essays](https://md.research.elamur.ai/free/en/papers/silveira-2026-neuro-symbolic-approaches-rubric-based/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/)

## References

62 references, 23 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alfonso Amayuelas, Xianjun Yang, Antonis Antoniades, Wenyue Hua, Liangming Pan, and William Yang Wang. 2024. Multiagent collaboration attack: Investigating adversarial attacks in large language model collaborations via debate. In Findings of the Association for Computational Linguistics: EMNLP 2024,… [find](https://scholar.google.com/scholar?q=Alfonso+Amayuelas%2C+Xianjun+Yang%2C+Antonis+Antoniades%2C+Wenyue+Hua%2C+Liangming+Pan%2C+and+William+Yang+Wang%2E+2024%2E+Multiagent+collaboration+attack%3A+Investigating+adversarial+attacks+in+large+language+model+)
2. Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, and Charles Sutton. 2021. [Program synthesis with large language models](https://md.research.elamur.ai/free/en/papers/austin-2021-program-synthesis-large-language-models/). arXiv preprint arXiv:2108.07732.
3. Maciej Besta, Nils Blach, Ales Kubicek, Robert Gerstenberger, Michal Podstawski, Lukas Gianinazzi, Joanna Gajda, Tomasz Lehmann, Hubert Niewiadomski, Piotr Nyczyk, and Torsten Hoefler. 2024. Graph of thoughts: Solving elaborate problems with large language models. In Proceedings of the AAAI Conferen… [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+Torsten+Hoefler%2E+2024%2E+Graph+of+)
4. Guangyao Chen, Siwei Dong, Yu Shu, Ge Zhang, Jaward Sesay, Börje F Karlsson, Jie Fu, and Yemin Shi. 2024a. Autoagents: A framework for automatic agent generation. In Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, pages 22–30. [find](https://scholar.google.com/scholar?q=Guangyao+Chen%2C+Siwei+Dong%2C+Yu+Shu%2C+Ge+Zhang%2C+Jaward+Sesay%2C+B%C3%B6rje+F+Karlsson%2C+Jie+Fu%2C+and+Yemin+Shi%2E+2024a%2E+Autoagents%3A+A+framework+for+automatic+agent+generation%2E+In+Proceedings+of+the+Thirty%2DThird+In)
5. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, and 39 others. 202… — [Evaluating Large Language Models Trained on Code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/)
6. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Cheng Qian, Chi-Min Chan, Yujia Qin, Ya-Ting Lu, Ruobing Xie, Zhiyuan Liu, Maosong Sun, and Jie Zhou. 2024b. [Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors](https://md.research.elamur.ai/free/en/papers/chen-2023-agentverse-facilitating-multi-agent/). In The Twelfth International Conference on…
7. Weize Chen, Jiarui Yuan, Chen Qian, Cheng Yang, Zhiyuan Liu, and Maosong Sun. 2025. Optima: Optimizing effectiveness and efficiency for llm-based multi-agent system. In Findings of the Association for Computational Linguistics: ACL 2025, pages 11534–11557. [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+2025%2E+Optima%3A+Optimizing+effectiveness+and+efficiency+for+llm%2Dbased+multi%2Dagent+system%2E+In+Findings+of+the+Association+for)
8. Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 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. 2024. [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 Proceedings of the 41st International Conference on Machine Learning.
10. Shangbin Feng, Zifeng Wang, Palash Goyal, Yike Wang, Weijia Shi, Huang Xia, Hamid Palangi, Luke Zettlemoyer, Yulia Tsvetkov, Chen-Yu Lee, and Tomas Pfister. 2025. Heterogeneous swarms: Jointly optimizing model roles and weights for multi-llm systems. In Advances in Neural Information Processing Syst… [find](https://scholar.google.com/scholar?q=Shangbin+Feng%2C+Zifeng+Wang%2C+Palash+Goyal%2C+Yike+Wang%2C+Weijia+Shi%2C+Huang+Xia%2C+Hamid+Palangi%2C+Luke+Zettlemoyer%2C+Yulia+Tsvetkov%2C+Chen%2DYu+Lee%2C+and+Tomas+Pfister%2E+2025%2E+Heterogeneous+swarms%3A+Jointly+optimiz)
11. Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024. [Large language model based multi-agents: A survey of progress and challenges](https://md.research.elamur.ai/free/en/papers/guo-2024-large-language-model-based/). In Proceedings of the 33rd International Joint Conference on Artificial Intelligence, pages 8048–805…
12. Pengfei He, Zhenwei Dai, Xianfeng Tang, Yue Xing, Hui Liu, Jingying Zeng, Qiankun Peng, Shrivats Agrawal, Samarth Varshney, Suhang Wang, Jiliang Tang, and Qi He. 2025. Attention knows whom to trust: attention-based trust management for llm multi-agent systems. arXiv preprint arXiv:2506.02546. — [arXiv:2506.02546](https://arxiv.org/abs/2506.02546) [find](https://scholar.google.com/scholar?q=Pengfei+He%2C+Zhenwei+Dai%2C+Xianfeng+Tang%2C+Yue+Xing%2C+Hui+Liu%2C+Jingying+Zeng%2C+Qiankun+Peng%2C+Shrivats+Agrawal%2C+Samarth+Varshney%2C+Suhang+Wang%2C+Jiliang+Tang%2C+and+Qi+He%2E+2025%2E+Attention+knows+whom+to+trust%3A+a)
13. 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.
14. 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/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 6609– 6625.
15. Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and Jürgen Schmidhuber. 2024. [Metagpt: Meta programming for a multi-agent collaborative framework](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/). In The T…
16. Shengran Hu, Cong Lu, and Jeff Clune. 2025. Automated design of agentic systems. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Shengran+Hu%2C+Cong+Lu%2C+and+Jeff+Clune%2E+2025%2E+Automated+design+of+agentic+systems%2E+In+The+Thirteenth+International+Conference+on+Learning+Representations%2E)
17. Bowen Jin, Chulin Xie, Jiawei Zhang, Kashob Kumar Roy, Yu Zhang, Zheng Li, Ruirui Li, Xianfeng Tang, Suhang Wang, Yu Meng, and Jiawei Han. 2024. [Graph chain-of-thought: Augmenting large language models by reasoning on graphs](https://md.research.elamur.ai/free/en/papers/jin-2024-graph-chain-thought-augmenting-large/). In Findings of the Association for Computational Linguistics: ACL 2024, pa…
18. Zixuan Ke, Austin Xu, Yifei Ming, Xuan-Phi Nguyen, Caiming Xiong, and Shafiq Joty. 2025. Mas-zero: Designing multi-agent systems with zero supervision. arXiv preprint arXiv:2505.14996. — [arXiv:2505.14996](https://arxiv.org/abs/2505.14996) [find](https://scholar.google.com/scholar?q=Zixuan+Ke%2C+Austin+Xu%2C+Yifei+Ming%2C+Xuan%2DPhi+Nguyen%2C+Caiming+Xiong%2C+and+Shafiq+Joty%2E+2025%2E+Mas%2Dzero%3A+Designing+multi%2Dagent+systems+with+zero+supervision%2E+arXiv+preprint+arXiv%3A2505%2E14996%2E+%E2%80%94+%5BarXiv%3A2505%2E1)
19. Boyi Li, Zhonghan Zhao, Der-Horng Lee, and Gaoang Wang. 2025a. Adaptive graph pruning for multi-agent communication. arXiv preprint arXiv:2506.02951. — [arXiv:2506.02951](https://arxiv.org/abs/2506.02951) [find](https://scholar.google.com/scholar?q=Boyi+Li%2C+Zhonghan+Zhao%2C+Der%2DHorng+Lee%2C+and+Gaoang+Wang%2E+2025a%2E+Adaptive+graph+pruning+for+multi%2Dagent+communication%2E+arXiv+preprint+arXiv%3A2506%2E02951%2E+%E2%80%94+%5BarXiv%3A2506%2E02951%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E02)
20. Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. 2023. [Camel: Communicative agents for" mind" exploration of large language model society](https://md.research.elamur.ai/free/en/papers/li-2023-camel-communicative-agents-mind/). Advances in Neural Information Processing Systems, 36:51991–52008.
21. Shiyuan Li, Yixin Liu, Qingsong Wen, Chengqi Zhang, and Shirui Pan. 2026. Assemble your crew: Automatic multi-agent communication topology design via autoregressive graph generation. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 40, pages 23142–23150. [find](https://scholar.google.com/scholar?q=Shiyuan+Li%2C+Yixin+Liu%2C+Qingsong+Wen%2C+Chengqi+Zhang%2C+and+Shirui+Pan%2E+2026%2E+Assemble+your+crew%3A+Automatic+multi%2Dagent+communication+topology+design+via+autoregressive+graph+generation%2E+In+Proceedings+of)
22. Xinyi Li, Sai Wang, Siqi Zeng, Yu Wu, and Yi Yang. 2024. A survey on llm-based multi-agent systems: workflow, infrastructure, and challenges. Vicinagearth, 1(1):9. [find](https://scholar.google.com/scholar?q=Xinyi+Li%2C+Sai+Wang%2C+Siqi+Zeng%2C+Yu+Wu%2C+and+Yi+Yang%2E+2024%2E+A+survey+on+llm%2Dbased+multi%2Dagent+systems%3A+workflow%2C+infrastructure%2C+and+challenges%2E+Vicinagearth%2C+1%281%29%3A9%2E)
23. Zherui Li, Yan Mi, Zhenhong Zhou, Houcheng Jiang, Guibin Zhang, Kun Wang, and Junfeng Fang. 2025b. Goal-aware identification and rectification of misinformation in multi-agent systems. arXiv preprint arXiv:2506.00509. — [arXiv:2506.00509](https://arxiv.org/abs/2506.00509) [find](https://scholar.google.com/scholar?q=Zherui+Li%2C+Yan+Mi%2C+Zhenhong+Zhou%2C+Houcheng+Jiang%2C+Guibin+Zhang%2C+Kun+Wang%2C+and+Junfeng+Fang%2E+2025b%2E+Goal%2Daware+identification+and+rectification+of+misinformation+in+multi%2Dagent+systems%2E+arXiv+preprint+)
24. Lei Liang, Mengshu Sun, Zhengke Gui, Zhongshu Zhu, Zhouyu Jiang, Ling Zhong, Yuan Qu, Peilong Zhao, Zhongpu Bo, Jin Yang, Huaidong Xiong, Lin Yuan, Jun Xu, Zaoyang Wang, Zhiqiang Zhang, Wen Zhang, Huajun Chen, Wenguang Chen, and Jun Zhou. 2025. Kag: Boosting llms in professional domains via knowledg… [find](https://scholar.google.com/scholar?q=Lei+Liang%2C+Mengshu+Sun%2C+Zhengke+Gui%2C+Zhongshu+Zhu%2C+Zhouyu+Jiang%2C+Ling+Zhong%2C+Yuan+Qu%2C+Peilong+Zhao%2C+Zhongpu+Bo%2C+Jin+Yang%2C+Huaidong+Xiong%2C+Lin+Yuan%2C+Jun+Xu%2C+Zaoyang+Wang%2C+Zhiqiang+Zhang%2C+Wen+Zhang%2C+Hua)
25. Jia Liu, Jie Shuai, and Xiyao Li. 2023. State machine of thoughts: Leveraging past reasoning trajectories for enhancing problem solving. arXiv preprint arXiv:2312.17445. — [arXiv:2312.17445](https://arxiv.org/abs/2312.17445) [find](https://scholar.google.com/scholar?q=Jia+Liu%2C+Jie+Shuai%2C+and+Xiyao+Li%2E+2023%2E+State+machine+of+thoughts%3A+Leveraging+past+reasoning+trajectories+for+enhancing+problem+solving%2E+arXiv+preprint+arXiv%3A2312%2E17445%2E+%E2%80%94+%5BarXiv%3A2312%2E17445%5D%28https%3A%2F%2Fa)
26. Jie Liu, Guohua Wang, Ronghui Yang, Jiajie Zeng, Mengchen Zhao, and Yi Cai. 2025. Rtadev: Intention aligned multi-agent framework for software development. In Findings of the Association for Computational Linguistics: ACL 2025, pages 1548–1581. [find](https://scholar.google.com/scholar?q=Jie+Liu%2C+Guohua+Wang%2C+Ronghui+Yang%2C+Jiajie+Zeng%2C+Mengchen+Zhao%2C+and+Yi+Cai%2E+2025%2E+Rtadev%3A+Intention+aligned+multi%2Dagent+framework+for+software+development%2E+In+Findings+of+the+Association+for+Computati)
27. Rui Miao, Yixin Liu, Yili Wang, Xu Shen, Yue Tan, Yiwei Dai, Shirui Pan, and Xin Wang. 2025. [Blindguard: Safeguarding llm-based multi-agent systems under unknown attacks](https://md.research.elamur.ai/free/en/papers/miao-2026-blindguard-safeguarding-llm-based-multi/). arXiv preprint arXiv:2508.08127.
28. Edward F Moore. 1956. Gedanken-experiments on sequential machines. Automata studies, 34:129–153. [find](https://scholar.google.com/scholar?q=Edward+F+Moore%2E+1956%2E+Gedanken%2Dexperiments+on+sequential+machines%2E+Automata+studies%2C+34%3A129%E2%80%93153%2E)
29. OpenAI. 2025. Gpt-5 nano model documentation. Accessed: 2025-10-01. [find](https://scholar.google.com/scholar?q=OpenAI%2E+2025%2E+Gpt%2D5+nano+model+documentation%2E+Accessed%3A+2025%2D10%2D01%2E)
30. Tushar Pandey, Ara Ghukasyan, Oktay Goktas, and Santosh Kumar Radha. 2025. Adaptive graph of thoughts: Test-time adaptive reasoning unifying chain, tree, and graph structures. arXiv preprint arXiv:2502.05078. — [arXiv:2502.05078](https://arxiv.org/abs/2502.05078) [find](https://scholar.google.com/scholar?q=Tushar+Pandey%2C+Ara+Ghukasyan%2C+Oktay+Goktas%2C+and+Santosh+Kumar+Radha%2E+2025%2E+Adaptive+graph+of+thoughts%3A+Test%2Dtime+adaptive+reasoning+unifying+chain%2C+tree%2C+and+graph+structures%2E+arXiv+preprint+arXiv%3A250)
31. 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)
32. Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2024. [Chatdev: Communicative agents for software development](https://md.research.elamur.ai/free/en/papers/qian-2023-chatdev-communicative-agents-software/). In Proceedings of the 62nd Annual Meeting of the Association for Computat…
33. Chen Qian, Zihao Xie, YiFei Wang, Wei Liu, Kunlun Zhu, Hanchen Xia, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, and Maosong Sun. 2025. Scaling large language model-based multi-agent collaboration. In The Thirteenth International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Chen+Qian%2C+Zihao+Xie%2C+YiFei+Wang%2C+Wei+Liu%2C+Kunlun+Zhu%2C+Hanchen+Xia%2C+Yufan+Dang%2C+Zhuoyun+Du%2C+Weize+Chen%2C+Cheng+Yang%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2025%2E+Scaling+large+language+model%2Dbased+multi%2Dagent+c)
34. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R Bowman. 2024. [Gpqa: A graduate-level google-proof q&a benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). In First Conference on Language Modeling.
35. Emanuele Rossi, Ben Chamberlain, Fabrizio Frasca, Davide Eynard, Federico Monti, and Michael Bronstein. 2020. Temporal graph networks for deep learning on dynamic graphs. arXiv preprint arXiv:2006.10637. — [arXiv:2006.10637](https://arxiv.org/abs/2006.10637) [find](https://scholar.google.com/scholar?q=Emanuele+Rossi%2C+Ben+Chamberlain%2C+Fabrizio+Frasca%2C+Davide+Eynard%2C+Federico+Monti%2C+and+Michael+Bronstein%2E+2020%2E+Temporal+graph+networks+for+deep+learning+on+dynamic+graphs%2E+arXiv+preprint+arXiv%3A2006%2E106)
36. Zijun Liu, Yanzhe Zhang, Peng Li, Yang Liu, and Diyi Yang. 2024. A dynamic llm-powered agent network for task-oriented agent collaboration. In First Conference on Language Modeling. [find](https://scholar.google.com/scholar?q=Zijun+Liu%2C+Yanzhe+Zhang%2C+Peng+Li%2C+Yang+Liu%2C+and+Diyi+Yang%2E+2024%2E+A+dynamic+llm%2Dpowered+agent+network+for+task%2Doriented+agent+collaboration%2E+In+First+Conference+on+Language+Modeling%2E)
37. Mohit Shridhar, Xingdi Yuan, Marc-Alexandre Côté, Yonatan Bisk, Adam Trischler, and Matthew Hausknecht. 2020. [Alfworld: Aligning text and embodied environments for interactive learning](https://md.research.elamur.ai/free/en/papers/shridhar-2020-alfworld-aligning-text-embodied-environments/). arXiv preprint arXiv:2010.03768.
38. Grégoire Mialon, Clémentine Fourrier, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2024. [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.
39. Khanh-Tung Tran, Dung Dao, Minh-Duong Nguyen, Quoc-Viet Pham, Barry O’Sullivan, and Hoang D Nguyen. 2025. Multi-agent collaboration mechanisms: A survey of llms. arXiv preprint arXiv:2501.06322. [find](https://scholar.google.com/scholar?q=Khanh%2DTung+Tran%2C+Dung+Dao%2C+Minh%2DDuong+Nguyen%2C+Quoc%2DViet+Pham%2C+Barry+O%E2%80%99Sullivan%2C+and+Hoang+D+Nguyen%2E+2025%2E+Multi%2Dagent+collaboration+mechanisms%3A+A+survey+of+llms%2E+arXiv+preprint+arXiv%3A2501%2E06322%2E)
40. 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)
41. Shilong Wang, Guibin Zhang, Miao Yu, Guancheng Wan, Fanci Meng, Chongye Guo, Kun Wang, and Yang Wang. 2025. [G-safeguard: A topology-guided security lens and treatment on llm-based multi-agent systems](https://md.research.elamur.ai/free/en/papers/wang-2025-g-safeguard-topology-guided-security/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume…
42. Wenhui Wang, Furu Wei, Li Dong, Hangbo Bao, Nan Yang, and Ming Zhou. 2020. Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers. Advances in Neural Information Processing Systems. [find](https://scholar.google.com/scholar?q=Wenhui+Wang%2C+Furu+Wei%2C+Li+Dong%2C+Hangbo+Bao%2C+Nan+Yang%2C+and+Ming+Zhou%2E+2020%2E+Minilm%3A+Deep+self%2Dattention+distillation+for+task%2Dagnostic+compression+of+pre%2Dtrained+transformers%2E+Advances+in+Neural+Inform)
43. 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.
44. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc V Le, and Denny Zhou. 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/). In Advances in Neural Information Processing Systems, volume 35, pages 24824–24837.
45. Ronald J Williams. 1992. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8(3):229–256. [find](https://scholar.google.com/scholar?q=Ronald+J+Williams%2E+1992%2E+Simple+statistical+gradient%2Dfollowing+algorithms+for+connectionist+reinforcement+learning%2E+Machine+learning%2C+8%283%29%3A229%E2%80%93256%2E)
46. Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang (Eric) Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Ahmed Awadallah, Ryen W. White, Doug Burger, and Chi Wang. 2024a. Autogen: Enabling next-gen llm applications via multi-agent conversations. In First Conference on Language Modeling… [find](https://scholar.google.com/scholar?q=Qingyun+Wu%2C+Gagan+Bansal%2C+Jieyu+Zhang%2C+Yiran+Wu%2C+Beibin+Li%2C+Erkang+%28Eric%29+Zhu%2C+Li+Jiang%2C+Xiaoyun+Zhang%2C+Shaokun+Zhang%2C+Ahmed+Awadallah%2C+Ryen+W%2E+White%2C+Doug+Burger%2C+and+Chi+Wang%2E+2024a%2E+Autogen%3A+Enabli)
47. Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William 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/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2369–…
48. Miao Yu, Shilong Wang, Guibin Zhang, Junyuan Mao, Chenlong Yin, Qijiong Liu, Kun Wang, Qingsong Wen, and Yang Wang. 2025. Netsafe: Exploring the topological safety of multi-agent system. In Findings of the Association for Computational Linguistics: ACL 2025, pages 2905–2938. [find](https://scholar.google.com/scholar?q=Miao+Yu%2C+Shilong+Wang%2C+Guibin+Zhang%2C+Junyuan+Mao%2C+Chenlong+Yin%2C+Qijiong+Liu%2C+Kun+Wang%2C+Qingsong+Wen%2C+and+Yang+Wang%2E+2025%2E+Netsafe%3A+Exploring+the+topological+safety+of+multi%2Dagent+system%2E+In+Findings+o)
49. Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Dongsheng Li, and Deqing Yang. 2025. Evoagent: Towards automatic multi-agent generation via evolutionary algorithms. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Lan… [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+2025%2E+Evoagent%3A+Towards+automatic+multi%2Dagent+generation+via+evolutionary+algorithms%2E+In+Proceedings+of+the+2025+Conferenc)
50. Yanwei Yue, Guibin Zhang, Boyang Liu, Guancheng Wan, Kun Wang, Dawei Cheng, and Yiyan Qi. 2025. [Masrouter: Learning to route llms for multi-agent systems](https://md.research.elamur.ai/free/en/papers/yue-2025-masrouter-learning-route-llms-multi/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 15549–15572.
51. Yifan Zeng, Yiran Wu, Xiao Zhang, Huazheng Wang, and Qingyun Wu. 2024. Autodefense: Multi-agent llm defense against jailbreak attacks. arXiv preprint arXiv:2403.04783. — [arXiv:2403.04783](https://arxiv.org/abs/2403.04783) [find](https://scholar.google.com/scholar?q=Yifan+Zeng%2C+Yiran+Wu%2C+Xiao+Zhang%2C+Huazheng+Wang%2C+and+Qingyun+Wu%2E+2024%2E+Autodefense%3A+Multi%2Dagent+llm+defense+against+jailbreak+attacks%2E+arXiv+preprint+arXiv%3A2403%2E04783%2E+%E2%80%94+%5BarXiv%3A2403%2E04783%5D%28https%3A%2F%2Farx)
52. Guibin Zhang, Kaijie Chen, Guancheng Wan, Heng Chang, Hong Cheng, Kun Wang, Shuyue Hu, and Lei Bai. 2025a. Evoflow: Evolving diverse agentic workflows on the fly. arXiv preprint arXiv:2502.07373. — [arXiv:2502.07373](https://arxiv.org/abs/2502.07373) [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Kaijie+Chen%2C+Guancheng+Wan%2C+Heng+Chang%2C+Hong+Cheng%2C+Kun+Wang%2C+Shuyue+Hu%2C+and+Lei+Bai%2E+2025a%2E+Evoflow%3A+Evolving+diverse+agentic+workflows+on+the+fly%2E+arXiv+preprint+arXiv%3A2502%2E07373%2E+%E2%80%94+%5Ba)
53. Guibin Zhang, Luyang Niu, Junfeng Fang, Kun Wang, Lei Bai, and Xiang Wang. 2025b. Multi-agent architecture search via agentic supernet. arXiv preprint arXiv:2502.04180. — [arXiv:2502.04180](https://arxiv.org/abs/2502.04180) [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Luyang+Niu%2C+Junfeng+Fang%2C+Kun+Wang%2C+Lei+Bai%2C+and+Xiang+Wang%2E+2025b%2E+Multi%2Dagent+architecture+search+via+agentic+supernet%2E+arXiv+preprint+arXiv%3A2502%2E04180%2E+%E2%80%94+%5BarXiv%3A2502%2E04180%5D%28https%3A%2F%2Far)
54. Yiran Wu, Tianwei Yue, Shaokun Zhang, Chi Wang, and Qingyun Wu. 2024b. [Stateflow: Enhancing llm task-solving through state-driven workflows](https://md.research.elamur.ai/free/en/papers/wu-2024-stateflow-enhancing-llm-task-solving/). arXiv preprint arXiv:2403.11322.
55. Guibin Zhang, Yanwei Yue, Xiangguo Sun, Guancheng Wan, Miao Yu, Junfeng Fang, Kun Wang, Tianlong Chen, and Dawei Cheng. 2025c. G-designer: Architecting multi-agent communication topologies via graph neural networks. In Proceedings of the 42nd International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Yanwei+Yue%2C+Xiangguo+Sun%2C+Guancheng+Wan%2C+Miao+Yu%2C+Junfeng+Fang%2C+Kun+Wang%2C+Tianlong+Chen%2C+and+Dawei+Cheng%2E+2025c%2E+G%2Ddesigner%3A+Architecting+multi%2Dagent+communication+topologies+via+graph+n)
56. Zhao Xinjie, Fan Gao, Xingyu Song, Yingjian Chen, Rui Yang, Yanran Fu, Yuyang Wang, Yusuke Iwasawa, Yutaka Matsuo, and Irene Li. 2025. [Reagent: Reversible multi-agent reasoning for knowledge-enhanced multi-hop qa](https://md.research.elamur.ai/free/en/papers/xinjie-2025-reagent-reversible-multi-agent-reasoning/). In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Process…
57. Jiayi Zhang, Jinyu Xiang, Zhaoyang Yu, Fengwei Teng, Xiong-Hui Chen, Jiaqi Chen, Mingchen Zhuge, Xin Cheng, Sirui Hong, Jinlin Wang, Bingnan Zheng, Bang Liu, Yuyu Luo, and Chenglin Wu. 2025d. Aflow: Automating agentic workflow generation. In The Thirteenth International Conference on Learning Repres… [find](https://scholar.google.com/scholar?q=Jiayi+Zhang%2C+Jinyu+Xiang%2C+Zhaoyang+Yu%2C+Fengwei+Teng%2C+Xiong%2DHui+Chen%2C+Jiaqi+Chen%2C+Mingchen+Zhuge%2C+Xin+Cheng%2C+Sirui+Hong%2C+Jinlin+Wang%2C+Bingnan+Zheng%2C+Bang+Liu%2C+Yuyu+Luo%2C+and+Chenglin+Wu%2E+2025d%2E+Aflow%3A+A)
58. Kuo Yang, Xingjie Yang, Linhui Yu, Qing Xu, Yan Fang, Xu Wang, Zhengyang Zhou, and Yang Wang. 2025. Mashost builds it all: Autonomous multi-agent system directed by reinforcement learning. arXiv preprint arXiv:2506.08507. — [arXiv:2506.08507](https://arxiv.org/abs/2506.08507) [find](https://scholar.google.com/scholar?q=Kuo+Yang%2C+Xingjie+Yang%2C+Linhui+Yu%2C+Qing+Xu%2C+Yan+Fang%2C+Xu+Wang%2C+Zhengyang+Zhou%2C+and+Yang+Wang%2E+2025%2E+Mashost+builds+it+all%3A+Autonomous+multi%2Dagent+system+directed+by+reinforcement+learning%2E+arXiv+prepr)
59. Yaolun Zhang, Xiaogeng Liu, and Chaowei Xiao. 2025e. Metaagent: Automatically constructing multi-agent systems based on finite state machines. In Proceedings of the 42nd International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Yaolun+Zhang%2C+Xiaogeng+Liu%2C+and+Chaowei+Xiao%2E+2025e%2E+Metaagent%3A+Automatically+constructing+multi%2Dagent+systems+based+on+finite+state+machines%2E+In+Proceedings+of+the+42nd+International+Conference+on+Ma)
60. Yusen Zhang, Ruoxi Sun, Yanfei Chen, Tomas Pfister, Rui Zhang, and Sercan Arik. 2024. Chain of agents: Large language models collaborating on long-context tasks. Advances in Neural Information Processing Systems. [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+2024%2E+Chain+of+agents%3A+Large+language+models+collaborating+on+long%2Dcontext+tasks%2E+Advances+in+Neural+Information+Process)
61. Han Zhou, Xingchen Wan, Ruoxi Sun, Hamid Palangi, Shariq Iqbal, Ivan Vulić, Anna Korhonen, and Sercan Ö Arık. 2025. Multi-agent design: Optimizing agents with better prompts and topologies. arXiv preprint arXiv:2502.02533. — [arXiv:2502.02533](https://arxiv.org/abs/2502.02533) [find](https://scholar.google.com/scholar?q=Han+Zhou%2C+Xingchen+Wan%2C+Ruoxi+Sun%2C+Hamid+Palangi%2C+Shariq+Iqbal%2C+Ivan+Vulic%CC%81%2C+Anna+Korhonen%2C+and+Sercan+%C3%96+Ar%C4%B1k%2E+2025%2E+Multi%2Dagent+design%3A+Optimizing+agents+with+better+prompts+and+topologies%2E+arXiv+pre)
62. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 2024. Gptswarm: Language agents as optimizable graphs. In Proceedings of the 41st International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Mingchen+Zhuge%2C+Wenyi+Wang%2C+Louis+Kirsch%2C+Francesco+Faccio%2C+Dmitrii+Khizbullin%2C+and+J%C3%BCrgen+Schmidhuber%2E+2024%2E+Gptswarm%3A+Language+agents+as+optimizable+graphs%2E+In+Proceedings+of+the+41st+International+)

*Updated 1 November 2026*