Simulating Dispute Mediation with LLM-Based Agents for Legal Research
This work provides a novel simulation platform for legal researchers to study dispute mediation, overcoming privacy and complexity limitations inherent in real-world empirical studies.
This paper introduces AgentMediation, an LLM-based agent framework designed to simulate legal dispute mediation. It allows for controlled experimentation on variables like disputant strategies and mediator expertise, revealing patterns consistent with sociological theories such as Group Polarization and Surface-level Consensus.
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.