Simulating Dispute Mediation with LLM-Based Agents for Legal Research

2025/09/08 by Junjie Chen, Chen, Junjie, Haitao Li +14 · 2 citations
Business, Management and Accounting · Computer Science · Social Sciences · #Artificial Intelligence in Law #Computers and Society (cs.CY) #Dispute Resolution and Class Actions #FOS: Computer and information sciences #Law, AI, and Intellectual Property

paper · pdf · doi:10.48550/arxiv.2509.06586

openalex publication_date 2025/09/08 · openalex created_date 2025/10/11 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• KODIS: A Multicultural Dispute Resolution Dialogue Corpus
• LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
• Emergent social conventions and collective bias in LLM populations
• Robots in the Middle: Evaluating LLMs in Dispute Resolution
• AgentReview: Exploring Peer Review Dynamics with LLM Agents
• AgentsCourt: Building Judicial Decision-Making Agents with Court Debate Simulation and Legal Knowledge Augmentation
• War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars
• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
• Generative Agents: Interactive Simulacra of Human Behavior
• CaSiNo: A Corpus of Campsite Negotiation Dialogues for Automatic\n Negotiation Systems
• Compliance, identification, and internalization three processes of attitude change
• The Common Ingroup Identity Model: Recategorization and the Reduction of Intergroup Bias

Cited by

• ProMediate: A Socio-cognitive framework for evaluating proactive agents in multi-party negotiation
• LLM Agents in Law: Taxonomy, Applications, and Challenges

Related

• Robots in the Middle: Evaluating LLMs in Dispute Resolution
• NomicLaw: Emergent Trust and Strategic Argumentation in LLMs During Collaborative Law-Making
• Mediation through Game Theory
• From Moderation to Mediation: Can LLMs Serve as Mediators in Online Flame Wars?
• Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction