Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction

Shengbin Yue, Ting Huang, Zheng Jia, Siyuan Wang, Shujun Liu +3 more
2/8/2025
cs.CLcs.AI

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

Large Language Models (LLMs) have significantly advanced legal intelligence, but the scarcity of scenario data impedes the progress toward interactive legal scenarios. This paper introduces a Multi-agent Legal Simulation Driver (MASER) to scalably generate synthetic data by simulating interactive legal scenarios. Leveraging real-legal case sources, MASER ensures the consistency of legal attributes between participants and introduces a supervisory mechanism to align participants' characters and behaviors as well as addressing distractions. A Multi-stage Interactive Legal Evaluation (MILE) benchmark is further constructed to evaluate LLMs' performance in dynamic legal scenarios. Extensive experiments confirm the effectiveness of our framework.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

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

90% match2025

Large Language Models Meet Legal Artificial Intelligence: A Survey

87% match1 repo202025

LLM Agents in Law: Taxonomy, Applications, and Challenges

87% match2026

MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning

87% match2025

Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration

87% match1 repo92024

LLMs in Interpreting Legal Documents

86% match2025

Cite this paper

@article{yue2025multiagent,
  title  = {Multi-Agent Simulator Drives Language Models for Legal Intensive Interaction},
  author = {Shengbin Yue and Ting Huang and Zheng Jia and Siyuan Wang and Shujun Liu and Yun Song and Xuanjing Huang and Zhongyu Wei},
  year   = {2025},
  eprint = {2502.06882},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.06882v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.06882.svg)](https://codeofpaper.com/paper/2502.06882)

Discussion