---
title: "War and Peace (WarAgent) — paper by Hua et al. (2023)"
description: "They build WarAgent, a multi-agent system in which each LLM-driven agent represents a country. 40 references, cited by 42 papers here."
authors: ["Wenyue Hua", "Lizhou Fan", "Lingyao Li", "Kai Mei", "Jianchao Ji", "Yingqiang Ge", "Libby Hemphill", "Yongfeng Zhang"]
year: 2023
venue: "arXiv:2311.17227"
source: "https://arxiv.org/abs/2311.17227"
doi: "10.48550/arxiv.2311.17227"
arxiv: "2311.17227"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/hua-2023-war-peace-waragent-large-language/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/hua-2023-war-peace-waragent-large-language/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2023](https://md.research.elamur.ai/free/en/papers/2023/page/10/) / War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars

# War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars

**Authors:** [Wenyue Hua](https://md.research.elamur.ai/free/en/authors/wenyue-hua/), [Lizhou Fan](https://md.research.elamur.ai/free/en/authors/lizhou-fan/), [Lingyao Li](https://md.research.elamur.ai/free/en/authors/lingyao-li/), [Kai Mei](https://md.research.elamur.ai/free/en/authors/kai-mei/), Jianchao Ji, Yingqiang Ge, [Libby Hemphill](https://md.research.elamur.ai/free/en/authors/libby-hemphill/) and [Yongfeng Zhang](https://md.research.elamur.ai/free/en/authors/yongfeng-zhang/) · **Year:** 2023 · **Venue:** arXiv:2311.17227 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2311.17227) · [PDF](https://arxiv.org/pdf/2311.17227) · [DOI 10.48550/arxiv.2311.17227](https://doi.org/10.48550/arxiv.2311.17227) · [arXiv 2311.17227](https://arxiv.org/abs/2311.17227) · [OpenAlex](https://openalex.org/W4389217265)

**Citations:** 12 citations (OpenAlex, 2026-10-14) · [42](https://md.research.elamur.ai/free/en/papers/hua-2023-war-peace-waragent-large-language/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The authors ask whether large language models can help study how international conflicts arise and whether historical wars could have been avoided. They build WarAgent, a multi-agent system in which each LLM-driven agent represents a country. Agents act in rounds, choosing diplomatic and military moves such as messaging other states, proposing alliances or non-intervention pacts, mobilizing, or waiting. Three historical settings are modeled: World War I, World War II, and the Warring States Period of ancient China. The study has three aims: checking how closely simulated decisions follow the documented course of history, testing whether some triggers for war (casus belli) matter more than others, and replaying scenarios under altered conditions to probe whether war was inevitable. According to the authors, agent interactions in these replays shed new light on what pushes states toward war or peace, while also exposing what current LLMs can and cannot do when modeling collective human behavior. The work matters as an early step toward computational history and as a safe testbed for policy-style "what-if" experiments. Code and data are publicly released.

## Key points
- WarAgent is presented as the first LLM-based multi-agent simulation of historical international conflicts, covering WWI (1914–1918), WWII (1939–1945), and the Warring States Period (770 BC – 221 BC).
- Three research questions guide the study: simulation effectiveness (RQ1), the relative weight of war triggers, or Casus Belli (RQ2), and War Inevitability (RQ3).
- Each round, country agents pick from a fixed action set, including "Send Message", "Request Military Alliance", "Request Non-Intervention Treaty", "General Mobilization", and "Wait without Action". For WSP, the states include Qin, Chu, Qi, Yan, Han, Zhao, and Wei.
- The work places itself among earlier multi-agent LLM systems such as Generative Agents, LLM-Debate, ChatEval, MAD, MetaGPT, ChatDev, Camel, and AgentVerse, and extends this line of work to historical simulation.
- Code and data are available at github.com/agiresearch/WarAgent.

*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

- [University of Michigan](https://md.research.elamur.ai/free/en/universities/university-of-michigan/) — University, Ann Arbor, United States · 94 works · 18,548 citations
- [Rutgers, The State University of New Jersey](https://md.research.elamur.ai/free/en/universities/rutgers-the-state-university-of-new-jersey/) — University, New Brunswick, United States · 42 works · 12,558 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 18,805 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 2,009 works · [🤝 Political Science and International Relations](https://md.research.elamur.ai/free/en/shelves/social-sciences/political-science-and-international-relations/) · 207 works

## Cite

Cite as: Wenyue Hua, Lizhou Fan, Lingyao Li, Kai Mei, Jianchao Ji, Yingqiang Ge, Libby Hemphill and Yongfeng Zhang. 2023. War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars. arXiv:2311.17227.

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

```bibtex
@misc{hua2023war,
  title = {{War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars}},
  author = {Wenyue Hua, Lizhou Fan, Lingyao Li, Kai Mei, Jianchao Ji, Yingqiang Ge, Libby Hemphill and Yongfeng Zhang},
  year = {2023},
  doi = {10.48550/arxiv.2311.17227},
  eprint = {2311.17227},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2311.17227}
}
```

- [← previous SLM: Bridge the thin gap between speech and text foundation models](https://md.research.elamur.ai/free/en/papers/wang-2023-slm-bridge-thin-gap-between/)
- [next → A Better Way to Do Masked Language Model Scoring](https://md.research.elamur.ai/free/en/papers/kauf-2023-better-way-do-masked-language/)
- [↑ back to papers of 2023](https://md.research.elamur.ai/free/en/papers/2023/page/10/)

## References

40 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Robert B Smith. Presidential decision-making during the cuban missile crisis: a computer simulation. Simulation & Games, 1(2):173–201, 1970. [find](https://scholar.google.com/scholar?q=Robert+B+Smith%2E+Presidential+decision%2Dmaking+during+the+cuban+missile+crisis%3A+a+computer+simulation%2E+Simulation+%26+Games%2C+1%282%29%3A173%E2%80%93201%2C+1970%2E)
2. Charles F Hermann and Margaret G Hermann. An attempt to simulate the outbreak of world war i. American Political Science Review, 61(2):400–416, 1967. [find](https://scholar.google.com/scholar?q=Charles+F+Hermann+and+Margaret+G+Hermann%2E+An+attempt+to+simulate+the+outbreak+of+world+war+i%2E+American+Political+Science+Review%2C+61%282%29%3A400%E2%80%93416%2C+1967%2E)
3. Joon Sung Park, Joseph C O’Brien, Carrie J Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. Generative agents: Interactive simulacra of human behavior. arXiv preprint arXiv:2304.03442, 2023. [find](https://scholar.google.com/scholar?q=Joon+Sung+Park%2C+Joseph+C+O%E2%80%99Brien%2C+Carrie+J+Cai%2C+Meredith+Ringel+Morris%2C+Percy+Liang%2C+and+Michael+S+Bernstein%2E+Generative+agents%3A+Interactive+simulacra+of+human+behavior%2E+arXiv+preprint+arXiv%3A2304%2E0344)
4. Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, and Yang Liu. [Exploring large language models for communication games: An empirical study on werewolf](https://md.research.elamur.ai/free/en/papers/xu-2023-exploring-large-language-models-communication/). arXiv preprint arXiv:2309.04658, 2023.
5. Jiangjie Chen, Siyu Yuan, Rong Ye, Bodhisattwa Prasad Majumder, and Kyle Richardson. Put your money where your mouth is: Evaluating strategic planning and execution of llm agents in an auction arena. arXiv preprint arXiv:2310.05746, 2023. — [arXiv:2310.05746](https://arxiv.org/abs/2310.05746) [find](https://scholar.google.com/scholar?q=Jiangjie+Chen%2C+Siyu+Yuan%2C+Rong+Ye%2C+Bodhisattwa+Prasad+Majumder%2C+and+Kyle+Richardson%2E+Put+your+money+where+your+mouth+is%3A+Evaluating+strategic+planning+and+execution+of+llm+agents+in+an+auction+arena%2E+)
6. Yingqiang Ge, Wenyue Hua, Kai Mei, Jianchao Ji, Juntao Tan, Shuyuan Xu, Zelong Li, and Yongfeng Zhang. OpenAGI: When LLM meets domain experts. In Thirty-seventh Conference on Neural Information Processing Systems, 2023. [find](https://scholar.google.com/scholar?q=Yingqiang+Ge%2C+Wenyue+Hua%2C+Kai+Mei%2C+Jianchao+Ji%2C+Juntao+Tan%2C+Shuyuan+Xu%2C+Zelong+Li%2C+and+Yongfeng+Zhang%2E+OpenAGI%3A+When+LLM+meets+domain+experts%2E+In+Thirty%2Dseventh+Conference+on+Neural+Information+Proces)
7. Yilun Du, Shuang Li, Antonio Torralba, Joshua B. Tenenbaum, and Igor Mordatch. [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/), 2023.
8. Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan Liu. [Chateval: Towards better llm-based evaluators through multi-agent debate](https://md.research.elamur.ai/free/en/papers/chan-2023-chateval-better-llm-based/), 2023.
9. Qiushi Sun, Zhangyue Yin, Xiang Li, Zhiyong Wu, Xipeng Qiu, and Lingpeng Kong. [Corex: Pushing the boundaries of complex reasoning through multi-model collaboration](https://md.research.elamur.ai/free/en/papers/sun-2023-corex-pushing-boundaries-complex-reasoning/), 2023.
10. Tian Liang, Zhiwei He, Wenxiang Jiao, Xing Wang, Yan Wang, Rui Wang, Yujiu Yang, Zhaopeng Tu, and Shuming Shi. [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/), 2023.
11. Zhilin Wang, Yu Ying Chiu, and Yu Cheung Chiu. Humanoid agents: Platform for simulating human-like generative agents, 2023. [find](https://scholar.google.com/scholar?q=Zhilin+Wang%2C+Yu+Ying+Chiu%2C+and+Yu+Cheung+Chiu%2E+Humanoid+agents%3A+Platform+for+simulating+human%2Dlike+generative+agents%2C+2023%2E)
12. Yao Fu, Hao Peng, Tushar Khot, and Mirella Lapata. [Improving language model negotiation with self-play and in-context learning from ai feedback](https://md.research.elamur.ai/free/en/papers/fu-2023-improving-language-model-negotiation-self/). arXiv preprint arXiv:2305.10142, 2023.
13. Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, et al. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.[00352, 2023](https://md.research.elamur.ai/free/en/papers/hong-2023-metagpt-meta-programming-multi/).
14. Zhiwei Liu, Weiran Yao, Jianguo Zhang, Le Xue, Shelby Heinecke, Rithesh Murthy, Yihao Feng, Zeyuan Chen, Juan Carlos Niebles, Devansh Arpit, et al. [Bolaa: Benchmarking and orchestrating llm-augmented autonomous agents](https://md.research.elamur.ai/free/en/papers/liu-2023-bolaa-benchmarking-orchestrating-llm-augmented/). arXiv preprint arXiv:2308.05960, 2023.
15. Chen Qian, Xin Cong, Wei Liu, Cheng Yang, Weize Chen, Yusheng Su, Yufan Dang, Jiahao Li, Juyuan Xu, Dahai Li, Zhiyuan Liu, and Maosong Sun. Communicative agents for software development, 2023. [find](https://scholar.google.com/scholar?q=Chen+Qian%2C+Xin+Cong%2C+Wei+Liu%2C+Cheng+Yang%2C+Weize+Chen%2C+Yusheng+Su%2C+Yufan+Dang%2C+Jiahao+Li%2C+Juyuan+Xu%2C+Dahai+Li%2C+Zhiyuan+Liu%2C+and+Maosong+Sun%2E+Communicative+agents+for+software+development%2C+2023%2E)
16. Yohei Nakajima. Babyagi. [https://github.com/yoheinakajima/babyagi](https://github.com/yoheinakajima/babyagi), 2023. [↗](https://github.com/yoheinakajima/babyagi)
17. Weize Chen, Yusheng Su, Jingwei Zuo, Cheng Yang, Chenfei Yuan, Chen Qian, Chi-Min Chan, Yujia Qin, Yaxi Lu, Ruobing Xie, et al. [Agentverse: Facilitating multi-agent collaboration and exploring emergent behaviors](https://md.research.elamur.ai/free/en/papers/chen-2023-agentverse-facilitating-multi-agent/) in agents. arXiv preprint arXiv:2308.10848, 2023.
18. Guohao Li, Hasan Abed Al Kader Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. Camel: Communicative agents for "mind" exploration of large scale language model society, 2023. [find](https://scholar.google.com/scholar?q=Guohao+Li%2C+Hasan+Abed+Al+Kader+Hammoud%2C+Hani+Itani%2C+Dmitrii+Khizbullin%2C+and+Bernard+Ghanem%2E+Camel%3A+Communicative+agents+for+%22mind%22+exploration+of+large+scale+language+model+society%2C+2023%2E)
19. Ted Dickson. The road to united states involvement in world war i: A simulation. OAH Magazine of History, 17(1):48–56, 2002. [find](https://scholar.google.com/scholar?q=Ted+Dickson%2E+The+road+to+united+states+involvement+in+world+war+i%3A+A+simulation%2E+OAH+Magazine+of+History%2C+17%281%29%3A48%E2%80%9356%2C+2002%2E)
20. Harold Steere Guetzkow, Chadwick F Alger, and Richard A Brody. Simulation in international relations: Developments for research and teaching. (No Title), 1963. [find](https://scholar.google.com/scholar?q=Harold+Steere+Guetzkow%2C+Chadwick+F+Alger%2C+and+Richard+A+Brody%2E+Simulation+in+international+relations%3A+Developments+for+research+and+teaching%2E+%28No+Title%29%2C+1963%2E)
21. Eric Tollefson, M Martin, Andrew Fletcher, and ARMY TRADOC ANALYSIS CENTER MON-TEREY CA. Onesaf objective system (oos) behavior model verification. US Army TRADOC Analysis Center–Monterey, Monterey, CA, 2008. [find](https://scholar.google.com/scholar?q=Eric+Tollefson%2C+M+Martin%2C+Andrew+Fletcher%2C+and+ARMY+TRADOC+ANALYSIS+CENTER+MON%2DTEREY+CA%2E+Onesaf+objective+system+%28oos%29+behavior+model+verification%2E+US+Army+TRADOC+Analysis+Center%E2%80%93Monterey%2C+Monterey%2C+C)
22. Kevin M Kelly, Craig Finch, David Tartaro, and Shiva Jaganathan. Creating a world war ii combat simulator using onesaf objective system. In Proceedings of the Interservice/Industry Training, Simulation, and Education Conference, pages 510–520, 2006. [find](https://scholar.google.com/scholar?q=Kevin+M+Kelly%2C+Craig+Finch%2C+David+Tartaro%2C+and+Shiva+Jaganathan%2E+Creating+a+world+war+ii+combat+simulator+using+onesaf+objective+system%2E+In+Proceedings+of+the+Interservice%2FIndustry+Training%2C+Simulatio)
23. Raymond R Hill, Lance E Champagne, and Joseph C Price. Using agent-based simulation and game theory to examine the wwii bay of biscay u-boat campaign. The Journal of Defense Modeling and Simulation, 1(2):99–109, 2004. [find](https://scholar.google.com/scholar?q=Raymond+R+Hill%2C+Lance+E+Champagne%2C+and+Joseph+C+Price%2E+Using+agent%2Dbased+simulation+and+game+theory+to+examine+the+wwii+bay+of+biscay+u%2Dboat+campaign%2E+The+Journal+of+Defense+Modeling+and+Simulation%2C+1)
24. Nelson F Liu, Kevin Lin, John Hewitt, Ashwin Paranjape, Michele Bevilacqua, Fabio Petroni, and Percy Liang. [Lost in the middle: How language models use long contexts](https://md.research.elamur.ai/free/en/papers/liu-2023-lost-middle-language-models-use/). arXiv preprint arXiv:2307.03172, 2023.
25. Chenghao Yang and Allyson Ettinger. Can you follow me? testing situational understanding in chatgpt. arXiv preprint arXiv:2310.16135, 2023. — [arXiv:2310.16135](https://arxiv.org/abs/2310.16135) [find](https://scholar.google.com/scholar?q=Chenghao+Yang+and+Allyson+Ettinger%2E+Can+you+follow+me%3F+testing+situational+understanding+in+chatgpt%2E+arXiv+preprint+arXiv%3A2310%2E16135%2C+2023%2E+%E2%80%94+%5BarXiv%3A2310%2E16135%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2310%2E16135%29)
26. Annika Mombauer. The origins of the First World War: controversies and consensus. Routledge, 2013. [find](https://scholar.google.com/scholar?q=Annika+Mombauer%2E+The+origins+of+the+First+World+War%3A+controversies+and+consensus%2E+Routledge%2C+2013%2E)
27. Otto Pick. Who pulled the trigger: Soviet historians and the origins of world war ii. Probs. Communism, 9:64, 1960. [find](https://scholar.google.com/scholar?q=Otto+Pick%2E+Who+pulled+the+trigger%3A+Soviet+historians+and+the+origins+of+world+war+ii%2E+Probs%2E+Communism%2C+9%3A64%2C+1960%2E)
28. Annette L Juliano. The warring states period—the state of qin, yan, chu, and pazyryk: A historical footnote. Source: Notes in the History of Art, 10(4):25–29, 1991. [find](https://scholar.google.com/scholar?q=Annette+L+Juliano%2E+The+warring+states+period%E2%80%94the+state+of+qin%2C+yan%2C+chu%2C+and+pazyryk%3A+A+historical+footnote%2E+Source%3A+Notes+in+the+History+of+Art%2C+10%284%29%3A25%E2%80%9329%2C+1991%2E)
29. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. [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, 2020.
30. OpenAI. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/), 2023.
31. Anthropic. Model card and evaluations for claude models. 2023. [find](https://scholar.google.com/scholar?q=Anthropic%2E+Model+card+and+evaluations+for+claude+models%2E+2023%2E)
32. John Keegan. The first world war. Random House, 2014. [find](https://scholar.google.com/scholar?q=John+Keegan%2E+The+first+world+war%2E+Random+House%2C+2014%2E)
33. Epps Vinh. Bailey,(2010). Information Theoretic Measures for Clusterings Comparison: Variants, Properties, Normalization and Correction for Chance. JMLR, pages 2837–2854, 2010. [find](https://scholar.google.com/scholar?q=Epps+Vinh%2E+Bailey%2C%282010%29%2E+Information+Theoretic+Measures+for+Clusterings+Comparison%3A+Variants%2C+Properties%2C+Normalization+and+Correction+for+Chance%2E+JMLR%2C+pages+2837%E2%80%932854%2C+2010%2E)
34. Anand Rajaraman and Jeffrey David Ullman. Mining of massive datasets. Cambridge University Press, 2011. [find](https://scholar.google.com/scholar?q=Anand+Rajaraman+and+Jeffrey+David+Ullman%2E+Mining+of+massive+datasets%2E+Cambridge+University+Press%2C+2011%2E)
35. Joshua M Epstein. Inverse generative social science: Backward to the future. Journal of artificial societies and social simulation: JASSS, 26(2), 2023. [find](https://scholar.google.com/scholar?q=Joshua+M+Epstein%2E+Inverse+generative+social+science%3A+Backward+to+the+future%2E+Journal+of+artificial+societies+and+social+simulation%3A+JASSS%2C+26%282%29%2C+2023%2E)
36. Arianna Dal Forno, Ugo Merlone, et al. A multi-agent simulation platform for modeling perfectly rational and bounded-rational agents in organizations. JASSS, 5:1–16, 2002. [find](https://scholar.google.com/scholar?q=Arianna+Dal+Forno%2C+Ugo+Merlone%2C+et+al%2E+A+multi%2Dagent+simulation+platform+for+modeling+perfectly+rational+and+bounded%2Drational+agents+in+organizations%2E+JASSS%2C+5%3A1%E2%80%9316%2C+2002%2E)
37. J Gary Polhill and BM Edmonds. Open access for social simulation. Journal of Artificial Societies and Social Simulation, 10(3):10–10, 2007. [find](https://scholar.google.com/scholar?q=J+Gary+Polhill+and+BM+Edmonds%2E+Open+access+for+social+simulation%2E+Journal+of+Artificial+Societies+and+Social+Simulation%2C+10%283%29%3A10%E2%80%9310%2C+2007%2E)
38. National Research Council et al. Defense modeling, simulation, and analysis: meeting the challenge. National Academies Press, 2006. [find](https://scholar.google.com/scholar?q=National+Research+Council+et+al%2E+Defense+modeling%2C+simulation%2C+and+analysis%3A+meeting+the+challenge%2E+National+Academies+Press%2C+2006%2E)
39. Dietrich Stauffer. Sociophysics simulations. arXiv preprint cond-mat/0210213, 2002. [find](https://scholar.google.com/scholar?q=Dietrich+Stauffer%2E+Sociophysics+simulations%2E+arXiv+preprint+cond%2Dmat%2F0210213%2C+2002%2E)
40. Ron Sun. Cognition and multi-agent interaction: From cognitive modeling to social simulation. Cambridge University Press, 2006. [find](https://scholar.google.com/scholar?q=Ron+Sun%2E+Cognition+and+multi%2Dagent+interaction%3A+From+cognitive+modeling+to+social+simulation%2E+Cambridge+University+Press%2C+2006%2E)

*Updated 3 November 2026*