---
title: "Understanding the Information Propagation Effects of"
description: "They introduce counterfactual metrics: CAPE, which tracks whether a forced change… 11.8% accuracy. 43 references, cited by 9 papers here."
authors: ["Xu Shen", "Yixin Liu", "Yiwei Dai", "Yili Wang", "Rui Miao", "Yue Tan", "Shirui Pan", "Xin Wang"]
year: 2025
venue: "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing"
source: "https://aclanthology.org/2025.emnlp-main.623/"
doi: "10.18653/v1/2025.emnlp-main.623"
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/shen-2025-understanding-information-propagation-effects-communication/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/shen-2025-understanding-information-propagation-effects-communication/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/) / Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems

# Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems

**Authors:** [Xu Shen](https://md.research.elamur.ai/free/en/authors/xu-shen/), [Yixin Liu](https://md.research.elamur.ai/free/en/authors/yixin-liu/), [Yiwei Dai](https://md.research.elamur.ai/free/en/authors/yiwei-dai/), [Yili Wang](https://md.research.elamur.ai/free/en/authors/yili-wang/), [Rui Miao](https://md.research.elamur.ai/free/en/authors/rui-miao/), [Yue Tan](https://md.research.elamur.ai/free/en/authors/yue-tan/), [Shirui Pan](https://md.research.elamur.ai/free/en/authors/shirui-pan/) and [Xin Wang](https://md.research.elamur.ai/free/en/authors/xin-wang/) · **Year:** 2025 · **Venue:** [Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing](https://md.research.elamur.ai/free/en/venues/emnlp/) ([EMNLP 2025](https://md.research.elamur.ai/free/en/venues/emnlp/2025/)) · **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/2025.emnlp-main.623/) · [PDF](https://aclanthology.org/2025.emnlp-main.623.pdf) · [DOI 10.18653/v1/2025.emnlp-main.623](https://doi.org/10.18653/v1/2025.emnlp-main.623) · [OpenAlex](https://openalex.org/W4416036604)

**Citations:** 6 citations (OpenAlex, 2026-10-14) · [9](https://md.research.elamur.ai/free/en/papers/shen-2025-understanding-information-propagation-effects-communication/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Automated topology designers for LLM-based multi-agent systems (MAS), such as AgentPrune, AgentDrop and G-Designer, tend to prune communication graphs for efficiency. They rarely ask when sparse or dense structures actually help collaboration. This paper addresses that question from a causal angle. The authors model a MAS as a directed acyclic graph of role-playing agents. They introduce counterfactual metrics: CAPE, which tracks whether a forced change in one agent's output flips the system's final correctness, and its topology-level extension TCTE. These metrics show a trade-off. Sparse graphs block the spread of one agent's mistakes but also hide useful insights. Dense graphs share insights widely but amplify errors. Moderately sparse graphs tend to perform best. Building on this, the authors propose EIB-Learner. It runs dual-view GNNs to simulate error suppression on a sparse graph and insight diffusion on a dense one, then fuses the learned connection scores per query. Across six benchmarks covering reasoning, math and code, the method improves accuracy, lowers token usage and resists prompt attacks. This offers principled guidance for designing agent communication.

## Key points
- New causal metrics: **CAPE** (Counterfactual Agent Propagation Effect) for single agents and **TCTE** (Total Counterfactual Topology Effect) for whole topologies. Both are based on do-interventions on agent outputs.
- Main empirical finding: moderate sparsity balances limiting error spread against keeping beneficial information flowing.
- **EIB-Learner** (Error-Insight Balanced Learner) combines sparse-view and dense-view GNN connectivity through query-aware adaptive fusion. Code is available at github.com/se7esx/EIB.
- Token cost is low:
  - On GSM8K, about 8.8e+06 tokens, versus 2.8e+07 for LLM-Debate and 1.2e+07 for a complete graph.
  - On MMLU, roughly 2.2–2.3e+05 tokens, versus 1.6e+06 for LLM-Debate.
- Under a single-agent system-prompt injection attack, chain and tree topologies lose up to 11.8% accuracy, while EIB-Learner loses only 1.24%.

*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

- [UNSW Sydney](https://md.research.elamur.ai/free/en/universities/unsw-sydney/) — University, Sydney, Australia · 34 works · 1,509 citations
- [Jilin University](https://md.research.elamur.ai/free/en/universities/jilin-university/) — University, Changchun, China · 25 works · 5,252 citations
- [Griffith University](https://md.research.elamur.ai/free/en/universities/griffith-university/) — University, Brisbane, Australia · 10 works · 4,223 citations

📚 Shelves (5): [🖥️ 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 · [💭 Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/) · 1,552 works · [💭 Social Psychology](https://md.research.elamur.ai/free/en/shelves/psychology/social-psychology/) · 306 works · [🌐 Computer Networks and Communications](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-networks-and-communications/) · 64 works

## Cite

Cite as: Xu Shen, Yixin Liu, Yiwei Dai, Yili Wang, Rui Miao, Yue Tan, Shirui Pan and Xin Wang. 2025. Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.

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

```bibtex
@inproceedings{shen2025understanding,
  title = {{Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems}},
  author = {Xu Shen, Yixin Liu, Yiwei Dai, Yili Wang, Rui Miao, Yue Tan, Shirui Pan and Xin Wang},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing},
  year = {2025},
  doi = {10.18653/v1/2025.emnlp-main.623},
  url = {https://doi.org/10.18653/v1/2025.emnlp-main.623}
}
```

- [← previous Understanding Figurative Meaning through Explainable Visual Entailment](https://md.research.elamur.ai/free/en/papers/saakyan-2025-understanding-figurative-meaning-through-explainable/)
- [next → URIEL+: Enhancing Linguistic Inclusion and Usability in a Typological and Multilingual Knowledge Base](https://md.research.elamur.ai/free/en/papers/khan-2025-uriel-enhancing-linguistic-inclusion-usability/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/6/)

## References

43 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Xiaohe Bo, Zeyu Zhang, Quanyu Dai, Xueyang Feng, Lei Wang, Rui Li, Xu Chen, and Ji-Rong Wen. 2024. Reflective multi-agent collaboration based on large language models. Advances in Neural Information Processing Systems, 37:138595–138631. [find](https://scholar.google.com/scholar?q=Xiaohe+Bo%2C+Zeyu+Zhang%2C+Quanyu+Dai%2C+Xueyang+Feng%2C+Lei+Wang%2C+Rui+Li%2C+Xu+Chen%2C+and+Ji%2DRong+Wen%2E+2024%2E+Reflective+multi%2Dagent+collaboration+based+on+large+language+models%2E+Advances+in+Neural+Information+P)
2. Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde De Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, and 1 others. 2021. [Evaluating large language models trained on code](https://md.research.elamur.ai/free/en/papers/chen-2021-evaluating-large-language-models-trained/). arXiv preprint arXiv:2107.03374.
3. 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.
4. Enjun Du, Xunkai Li, Tian Jin, Zhihan Zhang, Rong-Hua Li, and Guoren Wang. 2025a. Graphmas-ter: Automated graph synthesis via llm agents in data-limited environments. ArXiv preprint arXiv:2504.00711v2. — [arXiv:2504.00711](https://arxiv.org/abs/2504.00711) [find](https://scholar.google.com/scholar?q=Enjun+Du%2C+Xunkai+Li%2C+Tian+Jin%2C+Zhihan+Zhang%2C+Rong%2DHua+Li%2C+and+Guoren+Wang%2E+2025a%2E+Graphmas%2Dter%3A+Automated+graph+synthesis+via+llm+agents+in+data%2Dlimited+environments%2E+ArXiv+preprint+arXiv%3A2504%2E00711v2)
5. Enjun Du, Siyi Liu, and Yongqi Zhang. 2025b. Graphor-acle: A foundation model for knowledge graph reasoning. ArXiv preprint arXiv:2505.11125. — [arXiv:2505.11125](https://arxiv.org/abs/2505.11125) [find](https://scholar.google.com/scholar?q=Enjun+Du%2C+Siyi+Liu%2C+and+Yongqi+Zhang%2E+2025b%2E+Graphor%2Dacle%3A+A+foundation+model+for+knowledge+graph+reasoning%2E+ArXiv+preprint+arXiv%3A2505%2E11125%2E+%E2%80%94+%5BarXiv%3A2505%2E11125%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2505%2E11125%29)
6. Enjun Du, Siyi Liu, and Yongqi Zhang. 2025c. Mixture of length and pruning experts for knowledge graphs reasoning. ArXiv preprint arXiv:2507.20498. [find](https://scholar.google.com/scholar?q=Enjun+Du%2C+Siyi+Liu%2C+and+Yongqi+Zhang%2E+2025c%2E+Mixture+of+length+and+pruning+experts+for+knowledge+graphs+reasoning%2E+ArXiv+preprint+arXiv%3A2507%2E20498%2E)
7. 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.
8. Taicheng Guo, Xiuying Chen, Yaqi Wang, Ruidi Chang, Shichao Pei, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. 2024a. [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 Thirty-Third International Joint Conference on Artificial Intelligence, pages…
9. Xudong Guo, Kaixuan Huang, Jiale Liu, Wenhui Fan, Natalia Vélez, Qingyun Wu, Huazheng Wang, Thomas L Griffiths, and Mengdi Wang. 2024b. Embodied llm agents learn to cooperate in organized teams. In Language Gamification-NeurIPS 2024 Workshop. [find](https://scholar.google.com/scholar?q=Xudong+Guo%2C+Kaixuan+Huang%2C+Jiale+Liu%2C+Wenhui+Fan%2C+Natalia+V%C3%A9lez%2C+Qingyun+Wu%2C+Huazheng+Wang%2C+Thomas+L+Griffiths%2C+and+Mengdi+Wang%2E+2024b%2E+Embodied+llm+agents+learn+to+cooperate+in+organized+teams%2E+In+La)
10. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). In International Conference on Learning Representations.
11. Mengkang Hu, Pu Zhao, Can Xu, Qingfeng Sun, Jian-guang Lou, Qingwei Lin, Ping Luo, and Saravan Rajmohan. 2024a. Agentgen: Enhancing planning abilities for large language model based agent via environment and task generation. arXiv preprint arXiv:2408.00764. — [arXiv:2408.00764](https://arxiv.org/abs/2408.00764) [find](https://scholar.google.com/scholar?q=Mengkang+Hu%2C+Pu+Zhao%2C+Can+Xu%2C+Qingfeng+Sun%2C+Jian%2Dguang+Lou%2C+Qingwei+Lin%2C+Ping+Luo%2C+and+Saravan+Rajmohan%2E+2024a%2E+Agentgen%3A+Enhancing+planning+abilities+for+large+language+model+based+agent+via+environm)
12. Shengchao Hu, Li Shen, Ya Zhang, and Dacheng Tao. 2024b. Learning multi-agent communication from graph modeling perspective. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Shengchao+Hu%2C+Li+Shen%2C+Ya+Zhang%2C+and+Dacheng+Tao%2E+2024b%2E+Learning+multi%2Dagent+communication+from+graph+modeling+perspective%2E+In+International+Conference+on+Learning+Representations%2E)
13. Yoichi Ishibashi and Yoshimasa Nishimura. 2024. Self-organized agents: A llm multi-agent framework toward ultra large-scale code generation and optimization. arXiv preprint arXiv:2404.02183. — [arXiv:2404.02183](https://arxiv.org/abs/2404.02183) [find](https://scholar.google.com/scholar?q=Yoichi+Ishibashi+and+Yoshimasa+Nishimura%2E+2024%2E+Self%2Dorganized+agents%3A+A+llm+multi%2Dagent+framework+toward+ultra+large%2Dscale+code+generation+and+optimization%2E+arXiv+preprint+arXiv%3A2404%2E02183%2E+%E2%80%94+%5BarXiv%3A)
14. 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.
15. Shiyuan Li, Yixin Liu, Qingsong Wen, Chengqi Zhang, and Shirui Pan. 2025. Assemble your crew: Automatic multi-agent communication topology design via autoregressive graph generation. arXiv preprint arXiv:2507.18224. — [arXiv:2507.18224](https://arxiv.org/abs/2507.18224) [find](https://scholar.google.com/scholar?q=Shiyuan+Li%2C+Yixin+Liu%2C+Qingsong+Wen%2C+Chengqi+Zhang%2C+and+Shirui+Pan%2E+2025%2E+Assemble+your+crew%3A+Automatic+multi%2Dagent+communication+topology+design+via+autoregressive+graph+generation%2E+arXiv+preprint+ar)
16. Yunxuan Li, Yibing Du, Jiageng Zhang, Le Hou, Peter Grabowski, Yeqing Li, and Eugene Ie. 2024. Improving multi-agent debate with sparse communication topology. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 7281– 7294. [find](https://scholar.google.com/scholar?q=Yunxuan+Li%2C+Yibing+Du%2C+Jiageng+Zhang%2C+Le+Hou%2C+Peter+Grabowski%2C+Yeqing+Li%2C+and+Eugene+Ie%2E+2024%2E+Improving+multi%2Dagent+debate+with+sparse+communication+topology%2E+In+Findings+of+the+Association+for+Compu)
17. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Shuming Shi, and Zhaopeng Tu. 2024. [Encouraging divergent thinking in large language models through multi-agent debate](https://md.research.elamur.ai/free/en/papers/liang-2023-encouraging-divergent-thinking-large-language/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17…
18. Wang Ling, Dani Yogatama, Chris Dyer, and Phil Blunsom. 2017. Program induction by rationale generation: Learning to solve and explain algebraic word problems. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 158–167. [find](https://scholar.google.com/scholar?q=Wang+Ling%2C+Dani+Yogatama%2C+Chris+Dyer%2C+and+Phil+Blunsom%2E+2017%2E+Program+induction+by+rationale+generation%3A+Learning+to+solve+and+explain+algebraic+word+problems%2E+In+Proceedings+of+the+55th+Annual+Meetin)
19. Bang Liu, Xinfeng Li, Jiayi Zhang, Jinlin Wang, Tanjin He, Sirui Hong, Hongzhang Liu, Shaokun Zhang, Kaitao Song, Kunlun Zhu, and 1 others. 2025a. Advances and challenges in foundation agents: From brain-inspired intelligence to evolutionary, collaborative, and safe systems. arXiv preprint arXiv:250… — [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+2025a%2E+Advances+and+challenges+in+foundation+agents%3A+From+br)
20. Yixin Liu, Guibin Zhang, Kun Wang, Shiyuan Li, and Shirui Pan. 2025b. Graph-augmented large language model agents: Current progress and future prospects. arXiv preprint arXiv:2507.21407. — [arXiv:2507.21407](https://arxiv.org/abs/2507.21407) [find](https://scholar.google.com/scholar?q=Yixin+Liu%2C+Guibin+Zhang%2C+Kun+Wang%2C+Shiyuan+Li%2C+and+Shirui+Pan%2E+2025b%2E+Graph%2Daugmented+large+language+model+agents%3A+Current+progress+and+future+prospects%2E+arXiv+preprint+arXiv%3A2507%2E21407%2E+%E2%80%94+%5BarXiv%3A2507)
21. 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.
22. 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.
23. 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.
24. Chen Qian, Zihao Xie, Yifei Wang, Wei Liu, Yufan Dang, Zhuoyun Du, Weize Chen, Cheng Yang, Zhiyuan Liu, and Maosong Sun. 2025. Scaling large-language-model-based multi-agent collaboration. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Chen+Qian%2C+Zihao+Xie%2C+Yifei+Wang%2C+Wei+Liu%2C+Yufan+Dang%2C+Zhuoyun+Du%2C+Weize+Chen%2C+Cheng+Yang%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+2025%2E+Scaling+large%2Dlanguage%2Dmodel%2Dbased+multi%2Dagent+collaboration%2E+In+Internat)
25. 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.
26. 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.
27. Yashar Talebirad and Amirhossein Nadiri. 2023. Multi-agent collaboration: Harnessing the power of intelligent llm agents. arXiv preprint arXiv:2306.03314. [find](https://scholar.google.com/scholar?q=Yashar+Talebirad+and+Amirhossein+Nadiri%2E+2023%2E+Multi%2Dagent+collaboration%3A+Harnessing+the+power+of+intelligent+llm+agents%2E+arXiv+preprint+arXiv%3A2306%2E03314%2E)
28. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, and 1 others. 2024a. [A survey on large language model based autonomous agents](https://md.research.elamur.ai/free/en/papers/wang-2023-survey-large-language-model-based/). Frontiers of Computer Science, 18(6):186345.
29. Song Wang, Zhen Tan, Zihan Chen, Shuang Zhou, Tianlong Chen, and Jundong Li. 2025a. [Anymac: Cascading flexible multi-agent collaboration via next-agent prediction](https://md.research.elamur.ai/free/en/papers/wang-2025-anymac-cascading-flexible-multi-agent/). arXiv preprint arXiv:2506.17784.
30. Xu Wang, Zihao Li, Benyou Wang, Yan Hu, and Difan Zou. 2025b. [Model unlearning via sparse autoencoder subspace guided projections](https://md.research.elamur.ai/free/en/papers/wang-2025-model-unlearning-sparse-autoencoder-subspace/). Preprint, arXiv:2505.24428.
31. Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. [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/). In International Conference on Learning Representations.
32. Zhenhailong Wang, Shaoguang Mao, Wenshan Wu, Tao Ge, Furu Wei, and Heng Ji. 2024b. [Unleashing the emergent cognitive synergy in large language models: A task-solving agent through multi-persona self-collaboration](https://md.research.elamur.ai/free/en/papers/wang-2023-unleashing-emergent-cognitive-synergy-large/). In Proceedings of the 2024 Conference of the North American Chapter of the Association…
33. Zhexuan Wang, Yutong Wang, Xuebo Liu, Liang Ding, Miao Zhang, Jie Liu, and Min Zhang. 2025c. [Agentdropout: Dynamic agent elimination for token-efficient and high-performance llm-based multi-agent collaboration](https://md.research.elamur.ai/free/en/papers/wang-2025-agentdropout-dynamic-agent-elimination-token/). arXiv preprint arXiv:2503.18891.
34. 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.
35. Zihao Yi, Jiarui Ouyang, Yuwen Liu, Tianhao Liao, Zhe Xu, and Ying Shen. 2024. [A survey on recent advances in llm-based multi-turn dialogue systems](https://md.research.elamur.ai/free/en/papers/yi-2024-survey-recent-advances-llm-based/). arXiv preprint arXiv:2402.18013.
36. Guibin Zhang, Yanwei Yue, Zhixun Li, Sukwon Yun, Guancheng Wan, Kun Wang, Dawei Cheng, Jeffrey Xu Yu, and Tianlong Chen. 2025a. Cut the crap: An economical communication pipeline for llm-based multi-agent systems. In International Conference on Learning Representations. [find](https://scholar.google.com/scholar?q=Guibin+Zhang%2C+Yanwei+Yue%2C+Zhixun+Li%2C+Sukwon+Yun%2C+Guancheng+Wan%2C+Kun+Wang%2C+Dawei+Cheng%2C+Jeffrey+Xu+Yu%2C+and+Tianlong+Chen%2E+2025a%2E+Cut+the+crap%3A+An+economical+communication+pipeline+for+llm%2Dbased+multi%2Da)
37. Guibin Zhang, Yanwei Yue, Xiangguo Sun, Guancheng Wan, Miao Yu, Junfeng Fang, Kun Wang, Tianlong Chen, and Dawei Cheng. 2025b. G-designer: Architecting multi-agent communication topologies via graph neural networks. In Forty-second 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+2025b%2E+G%2Ddesigner%3A+Architecting+multi%2Dagent+communication+topologies+via+graph+n)
38. Jintian Zhang, Xin Xu, Ningyu Zhang, Ruibo Liu, Bryan Hooi, and Shumin Deng. 2024a. [Exploring collaboration mechanisms for llm agents: A social psychology view](https://md.research.elamur.ai/free/en/papers/zhang-2024-exploring-collaboration-mechanisms-llm-agents/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 14544– 14607.
39. Kechi Zhang, Jia Li, Ge Li, Xianjie Shi, and Zhi Jin. 2024b. [CodeAgent: Enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges](https://md.research.elamur.ai/free/en/papers/zhang-2024-codeagent-enhancing-code-generation-tool/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages…
40. 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)
41. Andy Zhou, Kai Yan, Michal Shlapentokh-Rothman, Haohan Wang, and Yu-Xiong Wang. 2024. Language agent tree search unifies reasoning, acting, and planning in language models. In Proceedings of the 41st International Conference on Machine Learning, pages 62138–62160. [find](https://scholar.google.com/scholar?q=Andy+Zhou%2C+Kai+Yan%2C+Michal+Shlapentokh%2DRothman%2C+Haohan+Wang%2C+and+Yu%2DXiong+Wang%2E+2024%2E+Language+agent+tree+search+unifies+reasoning%2C+acting%2C+and+planning+in+language+models%2E+In+Proceedings+of+the+41st+)
42. 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)
43. Mingchen Zhuge, Wenyi Wang, Louis Kirsch, Francesco Faccio, Dmitrii Khizbullin, and Jürgen Schmidhuber. 2024. Gptswarm: Language agents as optimizable graphs. In Forty-first 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+Forty%2Dfirst+International+Conference+o)

*Updated 30 October 2026*