Elamur Research⌕
☰
home / papers / 2026 / Chinese Court Simulation with LLM-Based Agents System

Chinese Court Simulation with LLM-Based Agents System

Paper · 2026 · Kaiyuan Zhang, Jiaqi Li, Yueyue Wu et al.

Summary

Mock trials are central to legal education but depend on tutors, venues and live participants, so few people can access them. Earlier LLM courtroom systems such as AgentCourt and AgentsCourt simulate only a simplified debate and lack rigorous evaluation. The authors build SimCourt, a multi-agent framework that follows the official structure of Chinese criminal trials. From a defendant's details, the indictment and the evidence, it generates a complete five-stage trial transcript ending in a judgment. Agents with Profile, Memory and Strategy modules, plus external legal tools, play the courtroom roles. Evaluation has two parts. First, predicted imprisonment, probation and fines are checked against real verdicts. Second, legal experts compare SimCourt's dialogue pairwise with real trial records and baseline systems across 30 aspects. SimCourt improves sentence prediction, and experts frequently preferred its agents to the real human judges and lawyers. Weaknesses remain in procedural legality and legal citation. The released code and benchmark support further work on legal-domain agent simulation.

Key points

  • The simulation covers 5 stages: Trial Preparation, Trial Investigation, Evidence Presentation, Trial Debate and Final Statement. Investigation and Evidence Presentation are new compared with earlier work, and the debate runs about 3 rounds.
  • It uses 5 roles (Judge, Prosecutor, Attorney, Defendant, Stenographer).
  • Judgment prediction is measured by hit rate and relative error for prison term, probation and fine.
  • Process evaluation covers 3 roles × 3 stages × 30 aspects, with three annotators per case. Their average Cohen's Kappa is 0.702.
  • Strengths in expert preference:
    • Prosecutor: preferred 96% of the time for handling objections and more than 94% of the time for logical accusation.
    • Judge: 88% in adversarial framing.
    • Attorney: 90% across all aspects of evidence presentation.
  • Weaker areas:
    • Judge: cross-examination legality control (62%) and neutrality control (58%).
    • Prosecutor: lawful questioning (52%).
    • An automatic LLM-based evaluation agreed poorly with the experts, so it was moved to an appendix.
  • Limitations: the framework handles only criminal cases and follows a fixed procedure. Code and data are available at github.com/Miracle-2001/SimCourt.

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

🎓Tsinghua UniversityBeijing · China415 works · 94,028 citations

 Fields, topics and concepts

📚 Shelves 3The field of science this work belongs to (OpenAlex fields).Social Sciences · 1,954 worksPolitical Science and International Relations · 206 worksLaw · 84 works

🧭 Topics 1Research subjects and languages the work is about.Legal AI · 150 works

Cite

Cite as Kaiyuan Zhang, Jiaqi Li, Yueyue Wu, Haitao Li, Cheng Luo, Shaokun Zou, Yujia Zhou, Weihang Su, Yiqun Liu and Qingyao Ai. 2026. Chinese Court Simulation with LLM-Based Agents System. 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.411

@inproceedings{zhang2026chinese,
  title = {{Chinese Court Simulation with LLM-Based Agents System}},
  author = {Kaiyuan Zhang, Jiaqi Li, Yueyue Wu, Haitao Li, Cheng Luo, Shaokun Zou, Yujia Zhou, Weihang Su, Yiqun Liu and Qingyao Ai},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.411},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.411}
}

References

26 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901.
  2. Guhong Chen, Liyang Fan, Zihan Gong, Nan Xie, Zixuan Li, Ziqiang Liu, Chengming Li, Qiang Qu, Shiwen Ni, and Min Yang. 2024. Agentcourt: Simulating court with adversarial evolvable lawyer agents. arXiv preprint arXiv:2408.08089. find
  3. Jiaxi Cui, Munan Ning, Zongjian Li, Bohua Chen, Yang Yan, Hao Li, Bin Ling, Yonghong Tian, and Li Yuan. 2023. Chatlaw: A multi-agent collaborative legal assistant with knowledge graph enhanced mixture-of-experts large language model. arXiv preprint arXiv:2306.16092.
  4. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. The llama 3 herd of models. arXiv e-prints, pages arXiv–2407.
  5. Team GLM, Aohan Zeng, Bin Xu, Bowen Wang, Chenhui Zhang, Da Yin, Dan Zhang, Diego Rojas, Guanyu Feng, Hanlin Zhao, and 1 others. 2024. Chatglm: A family of large language models from glm-130b to glm-4 all tools. arXiv preprint arXiv:2406.12793.
  6. 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… find
  7. Hamzeh Abu Issa, Thair Kaddumi, and Naji Alwerikat. 2023. The impact of moot courts on the quality of legal education: Students of the faculty of law at the applied science private university as a model. Journal of Higher Education Theory and Practice, 23(19):266–270. find
  8. Yiqiao Jin, Qinlin Zhao, Yiyang Wang, Hao Chen, Kaijie Zhu, Yijia Xiao, and Jindong Wang. 2024. Agentreview: Exploring peer review dynamics with llm agents. arXiv preprint arXiv:2406.12708.
  9. Haitao Li, Yunqiu Shao, Yueyue Wu, Qingyao Ai, Yixiao Ma, and Yiqun Liu. 2024a. Lecardv2: A large-scale chinese legal case retrieval dataset. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 2251–2260. find
  10. Zhiheng Xi, Wenxiang Chen, Xin Guo, Wei He, Yiwen Ding, Boyang Hong, Ming Zhang, Junzhe Wang, Senjie Jin, Enyu Zhou, and 1 others. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864.
  11. Chaojun Xiao, Haoxi Zhong, Zhipeng Guo, Cunchao Tu, Zhiyuan Liu, Maosong Sun, Yansong Feng, Xianpei Han, Zhen Hu, Heng Wang, and Jianfeng Xu. 2018. Cail2018: A large-scale legal dataset for judgment prediction. Preprint, arXiv:1807.02478.
  12. Junkai Li, Siyu Wang, Meng Zhang, Weitao Li, Yunghwei Lai, Xinhui Kang, Weizhi Ma, and Yang Liu. 2024b. Agent hospital: A simulacrum of hospital with evolvable medical agents. arXiv preprint arXiv:2405.02957. — [arXiv:2405.02957](https://arxiv.org/abs/2405.02957) find
  13. Chengxing Xie, Canyu Chen, Feiran Jia, Ziyu Ye, Kai Shu, Adel Bibi, Ziniu Hu, Philip Torr, Bernard Ghanem, and Guohao Li. 2024. Can large language model agents simulate human trust behaviors? arXiv preprint arXiv:2402.04559. — [arXiv:2402.04559](https://arxiv.org/abs/2402.04559) find
  14. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, and 1 others. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. find
  15. Yuzhuang Xu, Shuo Wang, Peng Li, Fuwen Luo, Xiaolong Wang, Weidong Liu, and Yang Liu. 2023. Exploring large language models for communication games: An empirical study on werewolf. arXiv preprint arXiv:2309.04658.
  16. Xinyi Mou, Xuanwen Ding, Qi He, Liang Wang, Jingcong Liang, Xinnong Zhang, Libo Sun, Jiayu Lin, Jie Zhou, Xuanjing Huang, and 1 others. 2024. From individual to society: A survey on social simulation driven by large language model-based agents. arXiv preprint arXiv:2412.03563. — [arXiv:2412.03563](https://arxiv.org/abs/2412.03563) find
  17. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, and 1 others. 2025. Qwen3 technical report. arXiv preprint arXiv:2505.09388.
  18. Chen Qian, Wei Liu, Hongzhang Liu, Nuo Chen, Yufan Dang, Jiahao Li, Cheng Yang, Weize Chen, Yusheng Su, Xin Cong, and 1 others. 2023. Chatdev: Communicative agents for software development. arXiv preprint arXiv:2307.07924.
  19. Aaditya Singh, Adam Fry, Adam Perelman, Adam Tart, Adi Ganesh, Ahmed El-Kishky, Aidan McLaughlin, Aiden Low, AJ Ostrow, Akhila Ananthram, and 1 others. 2025. Openai gpt-5 system card. arXiv preprint arXiv:2601.03267.
  20. Jiakai Tang, Heyang Gao, Xuchen Pan, Lei Wang, Haoran Tan, Dawei Gao, Yushuo Chen, Xu Chen, Yankai Lin, Yaliang Li, and 1 others. 2024. Gensim: A general social simulation platform with large language model based agents. arXiv preprint arXiv:2410.04360. find
  21. Lang Tang. 2021. The effective application of" moot court" in law teaching. In 2021 2nd International Conference on Computers, Information Processing and Advanced Education, pages 240–243. find
  22. Lei Wang, Jingsen Zhang, Xu Chen, Yankai Lin, Ruihua Song, Wayne Xin Zhao, and Ji-Rong Wen. 2023. Recagent: A novel simulation paradigm for recommender systems. arXiv preprint arXiv:2306.02552.
  23. Yiquan Wu, Siying Zhou, Yifei Liu, Weiming Lu, Xiaozhong Liu, Yating Zhang, Changlong Sun, Fei Wu, and Kun Kuang. 2023. Precedent-enhanced legal judgment prediction with llm and domain-model collaboration. arXiv preprint arXiv:2310.09241. find
  24. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations (ICLR).
  25. Hong Zhang. 2021. Construction of digital moot court teaching practice platform for law major. In 2021 4th International Conference on Information Systems and Computer Aided Education, pages 189–193. find
  26. Zeyu Zhang, Xiaohe Bo, Chen Ma, Rui Li, Xu Chen, Quanyu Dai, Jieming Zhu, Zhenhua Dong, and Ji-Rong Wen. 2024. A survey on the memory mechanism of large language model based agents. arXiv preprint arXiv:2404.13501. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-chinese-court-simulation-llm-based/