CoChat
Sign Up
PreprintCited by 45Multi-Agent Systems and NegotiationSimulation Techniques and ApplicationsOpinion Dynamics and Social Influence

AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society

Open access
Piao, Jinghua, Yan, Yuwei, Zhang, Jun, Li, Nian, Yan, Junbo, Lan, Xiaochong, Lu, Zhihong, Zheng, Zhiheng +8 more·2025·iFuture
DOI 10.2139/ssrn.5954414
Open this paper in CoChat — free account

Abstract

Abstract Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significant paradigmatic shift. By leveraging bottom-up simulations, it replaces costly and logistically challenging traditional experiments with scalable, replicable, and systematic computational approaches for studying complex social dynamics. Recent advances in large language models (LLMs) have further transformed this research paradigm, enabling the creation of human-like generative social agents and realistic simulacra of society. In this paper, we propose AgentSociety, a large-scale social simulator that integrates LLM-driven agents, a realistic societal environment, and a powerful large-scale simulation engine. Based on the proposed simulator, we generate social lives for over 10k agents, simulating their 5 million interactions both among agents and between agents and their environment. Furthermore, we explore the potential of AgentSociety as a testbed for computational social experiments, focusing on five key social issues: polarization, the spread of inflammatory messages, the effects of universal basic income policies, the impact of external shocks such as hurricanes, and urban sustainability. These five issues serve as valuable cases for assessing AgentSociety’s support for typical research methods – such as surveys, interviews, and interventions – as well as for investigating the patterns, causes, and underlying mechanisms of social issues. The alignment between AgentSociety’s outcomes and real-world experimental results not only demonstrates its ability to capture human behaviors and their underlying mechanisms, but also underscores its potential as an important platform for social scientists and policymakers.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.2139/ssrn.5954414

Cites

47 of 47 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • GenerativeAgents, AgentSociety, OpenClaw, and MoltBook show that many real agent workloads run in explicit rounds with a shared scheduler.

    “GenerativeAgents [26], AgentSociety [27], OpenClaw [24], and MoltBook [23] show that many real agent workloads run in explicit rounds with a shared scheduler.”

    From TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing (2026) · cites this paper as [27]

    In Social Simulator Performance (§6.3, p. 25), AgentSociety measures the time for agents to complete five interaction rounds, supporting the rounds part of the claim. The Group-based Distributed Execution discussion describes asynchronous, parallel execution without a required agent execution order; it does not establish a shared scheduler. This paper also cannot establish how the other three cited systems run. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • The All-Gather pattern is a natural starting point because it already appears across many agent workloads.

    “The All-Gather pattern is a natural starting point because it already appears across many agent workloads.”

    From TokenDance: Scaling Multi-Agent LLM Serving via Collective KV Cache Sharing (2026) · cites this paper as [27]

    Section 5.4 (pp. 20–21) describes MQTT messaging between agents, and Section 6.2 evaluates message throughput. Neither passage identifies an All-Gather pattern or says it appears across many agent workloads. Searched for “All-Gather,” “collective communication,” and gathering across agents. (LLM, conf=0.76)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 65

  1. [4]Gati V Aher, Rosa I Arriaga, and Adam Tauman Kalai. Using large language models to simulate multiple humans and replicate human subject studies. In International Conference on Machine Learning, pages 337–371. PMLR, 2023.
  2. [6]Altera AL, Andrew Ahn, Nic Becker, Stephanie Carroll, Nico Christie, Manuel Cortes, Arda Demirci, Melissa Du, Frankie Li, Shuying Luo, et al. Project sid: Many-agent simulations toward ai civilization. arXiv preprint arXiv:2411.00114, 2024. · arXiv
  3. [12]Robert L Axtell and J Doyne Farmer. Agent-based modeling in economics and finance: Past, present, and future. Journal of Economic Literature, pages 1–101, 2022.
  4. [17]Michael Behrisch, Laura Bieker, Jakob Erdmann, and Daniel Krajzewicz. Sumo–simulation of urban mobility: an overview. In Proceedings of SIMUL 2011, The Third International Conference on Advances in System Simulation. ThinkMind, 2011.
  5. [20]Mathieu Bourgais, Patrick Taillandier, Laurent Vercouter, and Carole Adam. Emotion modeling in social simulation: a survey. Journal of Artificial Societies and Social Simulation, 2018.
  6. [22]Leo Breiman. Statistical modeling: The two cultures (with comments and a rejoinder by the author). Statistical science, 16(3):199–231, 2001.
  7. [24]Junyan Cheng and Peter Chin. Sociodojo: Building lifelong analytical agents with real-world text and time series. In The Twelfth International Conference on Learning Representations, 2024.
  8. [26]Robert B Cialdini, Raymond R Reno, and Carl A Kallgren. A focus theory of normative conduct: Recycling the concept of norms to reduce littering in public places. Journal of personality and social psychology, 58(6):1015, 1990.
  9. [27]John Conway et al. The game of life. Scientific American, 223(4):4, 1970.
  10. [29]Dorottya Demszky, Diyi Yang, David S Yeager, Christopher J Bryan, Margarett Clapper, Susannah Chandhok, Johannes C Eichstaedt, Cameron Hecht, Jeremy Jamieson, Meghann Johnson, et al. Using large language models in psychology. Nature Reviews Psychology, 2(11):688–701, 2023.
  11. [32]Joshua M Epstein. Generative social science: Studies in agent-based computational modeling. Princeton University Press, 2012.
  12. [34]Jie Feng, Yuwei Du, Jie Zhao, and Yong Li. Agentmove: Predicting human mobility anywhere using large language model based agentic framework. arXiv preprint arXiv:2408.13986, 2024. · arXiv
  13. [36]Shuo Feng, Xintao Yan, Haowei Sun, Yiheng Feng, and Henry X Liu. Intelligent driving intelligence test for autonomous vehicles with naturalistic and adversarial environment. Nature communications, 12(1):748, 2021.
  14. [39]Chen Gao, Xiaochong Lan, Nian Li, Yuan Yuan, Jingtao Ding, Zhilun Zhou, Fengli Xu, and Yong Li. Large language models empowered agent-based modeling and simulation: A survey and perspectives. Humanities and Social Sciences Communications, 11(1):1–24, 2024.
  15. [40]Chen Gao, Xiaochong Lan, Zhihong Lu, Jinzhu Mao, Jinghua Piao, Huandong Wang, Depeng Jin, and Yong Li. S3: Social-network simulation system with large language model-empowered agents. arXiv preprint arXiv:2307.14984, 2023. · arXiv
  16. [41]Dawei Gao, Zitao Li, Xuchen Pan, Weirui Kuang, Zhijian Ma, Bingchen Qian, Fei Wei, Wenhao Zhang, Yuexiang Xie, Daoyuan Chen, et al. Agentscope: A flexible yet robust multi-agent platform. arXiv preprint arXiv:2402.14034, 2024. · arXiv
  17. [42]Birgitta Gatersleben, Niamh Murtagh, and Wokje Abrahamse. Values, identity and pro- environmental behaviour. Contemporary Social Science, 9(4):374–392, 2014.
  18. [45]Jing Guo, Nan Li, Jianchuan Qi, Hang Yang, Ruiqiao Li, Yuzhen Feng, Si Zhang, and Ming Xu. Empowering working memory for large language model agents. arXiv preprint arXiv:2312.17259, 2023. · arXiv
  19. [50]Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Jinlin Wang, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, et al. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352, 2023. · arXiv
  20. [52]Lei Huang, Weijiang Yu, Weitao Ma, Weihong Zhong, Zhangyin Feng, Haotian Wang, Qiang- long Chen, Weihua Peng, Xiaocheng Feng, Bing Qin, et al. A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions. ACM Transactions on Information Systems, 2023.
  21. [53]Qian Huang, Jian Vora, Percy Liang, and Jure Leskovec. Benchmarking large language models as ai research agents. In NeurIPS 2023 Foundation Models for Decision Making Workshop, 2023.
  22. [54]Yue Huang, Zhengqing Yuan, Yujun Zhou, Kehan Guo, Xiangqi Wang, Haomin Zhuang, Weixiang Sun, Lichao Sun, Jindong Wang, Yanfang Ye, et al. Social science meets llms: How reliable are large language models in social simulations? arXiv preprint arXiv:2410.23426, 2024. · arXiv
  23. [55]Zexun Jiang, Yafang Shi, Maoxu Li, Hongjiang Xiao, Yunxiao Qin, Qinglan Wei, Ye Wang, and Yuan Zhang. Casevo: A cognitive agents and social evolution simulator. arXiv preprint arXiv:2412.19498, 2024. · arXiv
  24. [56]Hamdi Kavak, Jose J Padilla, Christopher J Lynch, and Saikou Y Diallo. Big data, agents, and machine learning: towards a data-driven agent-based modeling approach. In Proceedings of the Annual Simulation Symposium, pages 1–12, 2018.
  25. [61]Shiyang Lai, Yujin Potter, Junsol Kim, Richard Zhuang, Dawn Song, and James Evans. Evolving ai collectives to enhance human diversity and enable self-regulation. arXiv preprint arXiv:2402.12590, 2024. · arXiv
  26. [63]Michael Laver and Ernest Sergenti. Party competition: An agent-based model, volume 20. Princeton University Press, 2011.
  27. [64]David Lazer, Alex Pentland, Lada Adamic, Sinan Aral, Albert-László Barabási, Devon Brewer, Nicholas Christakis, Noshir Contractor, James Fowler, Myron Gutmann, et al. Computational social science. Science, 323(5915):721–723, 2009.
  28. [65]David MJ Lazer, Alex Pentland, Duncan J Watts, Sinan Aral, Susan Athey, Noshir Contractor, Deen Freelon, Sandra Gonzalez-Bailon, Gary King, Helen Margetts, et al. Computational social science: Obstacles and opportunities. Science, 369(6507):1060–1062, 2020.
  29. [66]Guohao Li, Hasan Hammoud, Hani Itani, Dmitrii Khizbullin, and Bernard Ghanem. Camel: Communicative agents for" mind" exploration of large language model society. Advances in Neural Information Processing Systems, 36:51991–52008, 2023.
  30. [68]Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, et al. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437, 2024. · arXiv
  31. [69]Ruibo Liu, Ruixin Yang, Chenyan Jia, Ge Zhang, Denny Zhou, Andrew M Dai, Diyi Yang, and Soroush Vosoughi. Training socially aligned language models on simulated social interactions. arXiv preprint arXiv:2305.16960, 2023. · arXiv
  32. [70]Charles M Macal and Michael J North. Tutorial on agent-based modeling and simulation. In Proceedings of the Winter Simulation Conference, 2005., pages 14–pp. IEEE, 2005.
  33. [71]AH Maslow. A theory of human motivation. Psychological Review, 2:21–28, 1943.
  34. [72]Saul McLeod. Maslow's hierarchy of needs. Simply psychology, 1(1-18), 2007.
  35. Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, et al. Ray: A distributed framework for emerging {AI} applications. In 13th USENIX symposium on operating systems design and implementation (OSDI 18), pages 561–577, 2018.
  36. [75]Xinyi Mou, Zhongyu Wei, and Xuanjing Huang. Unveiling the truth and facilitating change: To- wards agent-based large-scale social movement simulation. arXiv preprint arXiv:2402.16333, 2024. · arXiv
  37. [78]Xianghe Pang, Shuo Tang, Rui Ye, Yuxin Xiong, Bolun Zhang, Yanfeng Wang, and Si- heng Chen. Self-alignment of large language models via monopolylogue-based social scene simulation. In Forty-first International Conference on Machine Learning, 2024.
  38. [79]Xianghe Pang, Shuo Tang, Rui Ye, Yuxin Xiong, Bolun Zhang, Yanfeng Wang, and Siheng Chen. Self-alignment of large language models via multi-agent social simulation. In ICLR 2024 Workshop on Large Language Model (LLM) Agents, 2024.
  39. [80]Joon Sung Park, Joseph O'Brien, Carrie Jun Cai, Meredith Ringel Morris, Percy Liang, and Michael S Bernstein. Generative agents: Interactive simulacra of human behavior. In Proceedings of the 36th annual acm symposium on user interface software and technology, pages 1–22, 2023.
  40. [81]Joon Sung Park, Carolyn Q Zou, Aaron Shaw, Benjamin Mako Hill, Carrie Cai, Mered- ith Ringel Morris, Robb Willer, Percy Liang, and Michael S Bernstein. Generative agent simulations of 1,000 people. arXiv preprint arXiv:2411.10109, 2024. · arXiv
  41. [83]Jinghua Piao, Zhihong Lu, Chen Gao, Fengli Xu, Fernando P Santos, Yong Li, and James Evans. Emergence of human-like polarization among large language model agents. arXiv preprint arXiv:2501.05171, 2025. · arXiv
  42. [84]David V Pynadath, Mei Si, and Stacy C Marsella. Modeling theory of mind and cognitive appraisal with decision-theoretic agents. Social emotions in nature and artifact: emotions in human and human-computer interaction, pages 70–87, 2011.
  43. [88]Jingqing Ruan, Yihong Chen, Bin Zhang, Zhiwei Xu, Tianpeng Bao, Hangyu Mao, Ziyue Li, Xingyu Zeng, Rui Zhao, et al. Tptu: Task planning and tool usage of large language model-based ai agents. In NeurIPS 2023 Foundation Models for Decision Making Workshop, 2023.
  44. [92]Shalom H Schwartz. Normative influences on altruism. In Advances in experimental social psychology, volume 10, pages 221–279. Elsevier, 1977.
  45. [93]Chenyang Shao, Fengli Xu, Bingbing Fan, Jingtao Ding, Yuan Yuan, Meng Wang, and Yong Li. Beyond imitation: Generating human mobility from context-aware reasoning with large language models. arXiv preprint arXiv:2402.09836, 2024. · arXiv
  46. [96]James WA Strachan, Dalila Albergo, Giulia Borghini, Oriana Pansardi, Eugenio Scaliti, Saurabh Gupta, Krati Saxena, Alessandro Rufo, Stefano Panzeri, Guido Manzi, et al. Testing theory of mind in large language models and humans. Nature Human Behaviour, pages 1–11, 2024.
  47. [97]Seungjong Sun, Eungu Lee, Dongyan Nan, Xiangying Zhao, Wonbyung Lee, Bernard J Jansen, and Jang Hyun Kim. Random silicon sampling: Simulating human sub-population opinion using a large language model based on group-level demographic information. arXiv preprint arXiv:2402.18144, 2024. · arXiv
  48. [98]Jiakai Tang, Heyang Gao, Xuchen Pan, Lei Wang, Haoran Tan, Dawei Gao, Yushuo Chen, Xu Chen, Yankai Lin, Yaliang Li, et al. Gensim: A general social simulation platform with large language model based agents. arXiv preprint arXiv:2410.04360, 2024. · arXiv
  49. [101]Sander van der Hoog. Deep learning in (and of) agent-based models: A prospectus. arXiv preprint arXiv:1706.06302, 2017. · arXiv
  50. [102]Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv:2305.16291, 2023. · arXiv
  51. [104]Lei Wang, Jingsen Zhang, Hao Yang, Zhi-Yuan Chen, Jiakai Tang, Zeyu Zhang, Xu Chen, Yankai Lin, Hao Sun, Ruihua Song, et al. User behavior simulation with large language model-based agents for recommender systems. ACM Transactions on Information Systems, 2024.
  52. [105]Yiding Wang, Yuxuan Chen, Fangwei Zhong, Long Ma, and Yizhou Wang. Simulating human-like daily activities with desire-driven autonomy. arXiv preprint arXiv:2412.06435, 2024. · arXiv
  53. [106]Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837, 2022.
  54. [107]U Wilensky. An Introduction to Agent-Based Modeling: Modeling Natural, Social, and Engineered Complex Systems with Netlogo. The MIT Press, 2015.
  55. [109]Stephen Wolfram. Cellular automata. Los Alamos Science, pages 09–01, 1983.
  56. Junzhe Wang, Senjie Jin, Enyu Zhou, et al. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864, 2023. · arXiv
  57. [111]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. arXiv preprint arXiv:2309.04658, 2023. · arXiv
  58. [112]Yuwei Yan, Qingbin Zeng, Zhiheng Zheng, Jingzhe Yuan, Jie Feng, Jun Zhang, Fengli Xu, and Yong Li. Opencity: A scalable platform to simulate urban activities with massive llm agents. arXiv preprint arXiv:2410.21286, 2024. · arXiv
  59. [113]Ziyi Yang, Zaibin Zhang, Zirui Zheng, Yuxian Jiang, Ziyue Gan, Zhiyu Wang, Zijian Ling, Jinsong Chen, Martz Ma, Bowen Dong, et al. Oasis: Open agents social interaction simulations on one million agents. arXiv preprint arXiv:2411.11581, 2024. · arXiv
  60. [114]An Zhang, Yuxin Chen, Leheng Sheng, Xiang Wang, and Tat-Seng Chua. On generative agents in recommendation. In Proceedings of the 47th international ACM SIGIR conference on research and development in Information Retrieval, pages 1807–1817, 2024.
  61. [115]Chaoyun Zhang, Shilin He, Jiaxu Qian, Bowen Li, Liqun Li, Si Qin, Yu Kang, Minghua Ma, Qingwei Lin, Saravan Rajmohan, et al. Large language model-brained gui agents: A survey. arXiv preprint arXiv:2411.18279, 2024. · arXiv
  62. [117]Xinnong Zhang, Jiayu Lin, Libo Sun, Weihong Qi, Yihang Yang, Yue Chen, Hanjia Lyu, Xinyi Mou, Siming Chen, Jiebo Luo, et al. Electionsim: Massive population election simulation powered by large language model driven agents. arXiv preprint arXiv:2410.20746, 2024. · arXiv
  63. [118]Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. A survey on the memory mechanism of large language model based agents. arXiv preprint arXiv:2404.13501, 2024. · arXiv
  64. [120]Xuhui Zhou, Hao Zhu, Leena Mathur, Ruohong Zhang, Haofei Yu, Zhengyang Qi, Louis- Philippe Morency, Yonatan Bisk, Daniel Fried, Graham Neubig, et al. Sotopia: Interactive evaluation for social intelligence in language agents. arXiv preprint arXiv:2310.11667, 2023. · arXiv
  65. [121]Xizhou Zhu, Yuntao Chen, Hao Tian, Chenxin Tao, Weijie Su, Chenyu Yang, Gao Huang, Bin Li, Lewei Lu, Xiaogang Wang, et al. Ghost in the minecraft: Generally capable agents for open-world environments via large language models with text-based knowledge and memory. arXiv preprint arXiv:2305.17144, 2023. · arXiv

Cited by

Sorted by citations

Related

Authors
Piao, J., Yan, Y., Zhang, J., Li, N., Yan, J., Lan, X., Lu, Z., Zheng, Z., Wang, J. Y., Zhou, D., Gao, C., Xu, F., Zhang, F., Rong, K., Su, J., & Li, Y.
Affiliations
  • Tsinghua University (CN)
  • Tsinghua Shenzhen International Graduate School (CN)
Corresponding author
Li, Yong
ORCID
Venue
iFuture
Publisher
Elsevier BV
Published
2025
ISSN
3135-3169 (ISSN-L)
DOI
10.2139/ssrn.5954414
OpenAlex
W4407570917
Cited by
43
References
47
Citations by year
2026: 38 · 2025: 5
FWCI
129.86
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • iFuture (publishedVersion, cc-by)
  • SSRN Electronic Journal (acceptedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Multi-Agent Systems and Negotiation
  • Social Sciences › Decision Sciences › Management Science and Operations Research › Simulation Techniques and Applications
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Opinion Dynamics and Social Influence
Keywords
large language models, social simulation, polarization, universal basic income, hurricane impacts, urban sustainability, social dynamics

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review