Simulating Dispute Mediation with LLM-Based Agents for Legal Research
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29368-29375
DOI: 10.1609/aaai.v40i35.40177 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Junjie Chen und 8 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref).
Abstract (Originalsprache)
Legal dispute mediation plays a crucial role in resolving civil disputes, yet its empirical study is limited by privacy constraints and complex multivariate interactions. To address this limitation, we present AgentMediation, the first LLM-based agent framework for simulating dispute mediation. It simulates realistic mediation processes grounded in real-world disputes and enables controlled experimentation on key variables such as disputant strategies, dispute causes, and mediator expertise. Our empirical analysis reveals patterns consistent with sociological theories, including Group Polarization and Surface-level Consensus. As a comprehensive and extensible platform, AgentMediation paves the way for deeper integration of social science and AI in legal research.
Zitieren
APA
Chen, J., Li, H., Qin, M., Zhou, Y., Ren, Y., Wang, W., Liu, Y., Wu, Y., & Ai, Q. (2026). Simulating Dispute Mediation with LLM-Based Agents for Legal Research. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29368-29375. https://doi.org/10.1609/aaai.v40i35.40177
Vancouver
Chen J, Li H, Qin M, Zhou Y, Ren Y, Wang W, et al. Simulating Dispute Mediation with LLM-Based Agents for Legal Research. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29368-29375. doi:10.1609/aaai.v40i35.40177
BibTeX
@article{Chen2026,
author = {Chen, Junjie and Li, Haitao and Qin, Minghao and Zhou, Yujia and Ren, Yanxue and Wang, Wuyue and Liu, Yiqun and Wu, Yueyue and Ai, Qingyao},
title = {Simulating Dispute Mediation with LLM-Based Agents for Legal Research},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {35},
pages = {29368--29375},
doi = {10.1609/aaai.v40i35.40177}
}
EUVIMED