Elamur Research⌕
☰
home / papers / 2026 / Law in Silico: Simulating Legal Society with LLM-Based Agents

Law in Silico: Simulating Legal Society with LLM-Based Agents

Paper · 2026 · Yiding Wang, Yuxuan Chen, Fanxu Meng et al.

Summary

Testing legal theories or policies in the real world is often expensive or impossible. This paper asks whether LLM-driven agents can act as a stand-in "legal society" for such experiments. The authors build Law in Silico, a framework with three parts. Agents get hierarchical profiles drawn from sociological statistics. An LLM Game Master interprets agent actions and their consequences. Institutional modules cover legislation, adjudication and enforcement.

First, agent crime behavior is checked against real crime data from four countries, and it broadly reproduces known sociological correlations. Next, micro-level conflict scenarios (labor disputes, industrial pollution) let legal rules emerge from agent–institution interaction. Finally, these evolved laws are applied to large agent populations, a "Micro-to-Macro" loop.

As the law matures, exploitation and extra-legal resistance give way to compliance and lawsuits. Transparent, adaptive institutions dampen "cat-and-mouse" evasion and better shield vulnerable parties. The work matters because it offers a controllable sandbox for trying out regulations before deployment.

Key points

  • Calibration uses official crime statistics from four countries. Agents are profiled by factors such as income, education and drug use.
  • There are two conflict scenarios:
    • Labor: Companies can raise safety investment, keep the status quo, or shift costs. Laborers can submit, sabotage, sue or strike.
    • Pollution: Factories can downgrade safety, keep the status quo, or upgrade safety. Residents can buy purifiers, sue, protest or endure.
  • Evolved laws are evaluated at three snapshots: No Law, Middle Stage, and After Evolution. Sabotage declines and Companies move toward compliant strategies.
  • In a punishment-perception stress test (levels 0–5), crime falls from high at level 0 to near zero by level 3, consistent with deterrence theory.
  • Code is released at MuLabPKU/Law-in-Silico. Stated limitations are underreported official crime data, no modeling of stare decisis, and dependence on LLM biases.

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

🎓Peking UniversityBeijing · China244 works · 39,359 citations🎓Yale UniversityNew Haven · United States95 works · 12,765 citations🎓University of Hong KongPok Fu Lam · China89 works · 11,774 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksSocial Sciences · 1,772 worksSafety Research · 543 worksPolitical Science and International Relations · 182 works

🧭 Topics 1Research subjects and languages the work is about.Legal AI · 134 works

Cite

Cite as Yiding Wang, Yuxuan Chen, Fanxu Meng, Xifan Chen, Xiaolei Yang and Muhan Zhang. 2026. Law in Silico: Simulating Legal Society with LLM-Based Agents. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.396

@inproceedings{wang2026law,
  title = {{Law in Silico: Simulating Legal Society with LLM-Based Agents}},
  author = {Yiding Wang, Yuxuan Chen, Fanxu Meng, Xifan Chen, Xiaolei Yang and Muhan Zhang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.396},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.396}
}

References

29 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Michael Aikenhead, Robin Widdison, and Tom Allen. 1999. Exploring law through computer simulation. International Journal of Law and Information Technology, 7(3):191–217. ↗
  2. Gary S Becker. 1968. Crime and punishment: An economic approach. Journal of political economy, 76(2):169–217. ↗
  3. Ngoc Bui, Hieu Trung Nguyen, Shantanu Kumar, Julian Theodore, Weikang Qiu, Viet Anh Nguyen, and Rex Ying. 2025. Mixture-of-personas language models for population simulation. ArXiv, abs/2504.05019. ↗
  4. Aaron Chalfin and Justin McCrary. 2017. Criminal deterrence: A review of the literature. Journal of Economic Literature, 55(1):5–48. ↗
  5. Marc Galanter. 1974. Why the “haves” come out ahead: Speculations on the limits of legal change. Law & society review, 9(1):95–160. ↗
  6. Nigel Gilbert and Jim Doran. 2018. Simulating societies: the computer simulation of social phenomena. Routledge, London. find
  7. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, Amy Yang, Angela Fan, Anirudh Goyal, Anthony Hartshorn, Aobo Yang, Archi Mitra, Archie Sravankumar, Artem Korenev, Arthur Hinsvark, and 81 others. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783. ↗
  8. Zhitao He, Pengfei Cao, Chenhao Wang, Zhuoran Jin, Yubo Chen, Jiexin Xu, Huaijun Li, Kang Liu, and Jun Zhao. 2024. AgentsCourt: Building judicial decision-making agents with court debate simulation and legal knowledge augmentation. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9399–9416, Miami, Florida, USA. Association for Computational Linguistics. find
  9. Cong Jiang and Xiaolei Yang. 2024. Agents on the bench: Large language model based multi agent framework for trustworthy digital justice. arXiv preprint arXiv:2412.18697. ↗
  10. Simha F Landau. 1997. Crime patterns and their relation to subjective social stress and support indicators: The role of gender. Journal of Quantitative Criminology, 13(1):29–56. ↗
  11. Daniel S Nagin. 2013. Deterrence in the twenty-first century. Crime and justice, 42(1):199–263. ↗
  12. OpenAI, Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, Red Avila, Igor Babuschkin, Suchir Balaji, Valerie Balcom, Paul Baltescu, Haiming Bao, Mohammad Bavarian, Jeff Belgum, and 262 others. 2024. Gpt-4 technical report. Preprint, arXiv:2303.08774. ↗
  13. 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, UIST ’23, New York, NY, USA. Association for Computing Machinery. find
  14. Jinghua Piao, Yuwei Yan, Jun Zhang, Nian Li, Junbo Yan, Xiaochong Lan, Zhihong Lu, Zhiheng Zheng, Jing Yi Wang, and Di Zhou. 2025. Agentsociety: Large-scale simulation of llm-driven generative agents advances understanding of human behaviors and society. arXiv preprint arXiv:2502.08691. ↗
  15. Qwen, An Yang, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chengyuan Li, Dayiheng Liu, Fei Huang, Haoran Wei, Huan Lin, Jian Yang, Jianhong Tu, Jianwei Zhang, Jianxin Yang, Jiaxi Yang, Jingren Zhou, Junyang Lin, and 24 others. 2025. Qwen2.5 technical report. Preprint, arXiv:2412.15115. ↗
  16. Susan Rose-Ackerman. 2013. Corruption: A study in political economy. Academic press. find
  17. Rebecca L Sandefur. 2008. Access to civil justice and race, class, and gender inequality. Annu. Rev. Sociol, 34(1):339–358. ↗
  18. Marek J. Sergot, Fariba Sadri, Robert A. Kowalski, Frank Kriwaczek, Peter Hammond, and H Terese Cory. 1986. The british nationality act as a logic program. Communications of the ACM, 29(5):370–386. ↗
  19. Chirag Shah, Aman Chadha, Tanya Roosta, and Julia Kharchenko. 2024. How well do llms represent values across cultures? empirical analysis of llm responses based on hofstede cultural dimensions. ArXiv, abs/2406.14805. ↗
  20. Jingyun Sun, Chengxiao Dai, Zhongze Luo, Yangbo Chang, and Yang Li. 2024. Lawluo: A multi-agent collaborative framework for multi-round chinese legal consultation. arXiv preprint arXiv:2407.16252. ↗
  21. Tom R Tyler. 1990. Why people obey the law. Yale University. find
  22. Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023a. Voyager: An open-ended embodied agent with large language models. arXiv preprint arXiv: Arxiv-2305.16291. find
  23. Jiawei Wang, Renhe Jiang, Chuang Yang, Zengqing Wu, Ryosuke Shibasaki, Noboru Koshizuka, and Chuan Xiao. 2024a. Large language models as urban residents: An llm agent framework for personal mobility generation. Advances in Neural Information Processing Systems, 37:124547–124574. find
  24. Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Jirong Wen. 2024b. A survey on large language model based autonomous agents. Frontiers of Computer Science, 18(6). ↗
  25. Lei Wang, Chengbang Ma, Xueyang Feng, Zeyu Zhang, Hao ran Yang, Jingsen Zhang, Zhi-Yang Chen, Jiakai Tang, Xu Chen, Yankai Lin, Wayne Xin Zhao, Zhewei Wei, and Ji rong Wen. 2023b. A survey on large language model based autonomous agents. Frontiers Comput. Sci., 18:186345.
  26. Yiding Wang, Yuxuan Chen, Fangwei Zhong, Long Ma, and Yizhou Wang. 2024c. Simulating human-like daily activities with desire-driven autonomy. arXiv preprint arXiv:2412.06435. ↗
  27. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Ed H. Chi, F. Xia, Quoc Le, and Denny Zhou. 2022. Chain of thought prompting elicits reasoning in large language models. ArXiv, abs/2201.11903. ↗
  28. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations.
  29. Shengbin Yue, Ting Huang, Zheng Jia, Siyuan Wang, Shujun Liu, Yun Song, Xuanjing Huang, and Zhongyu Wei. 2025. Multi-agent simulator drives language models for legal intensive interaction. In Findings of the Association for Computational Linguistics: NAACL 2025, pages 6537–6570, Albuquerque, New Mexico. Association for Computational Linguistics. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-law-silico-simulating-legal-society/