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.
@article{arxiv.2502.06882,
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},
journal= {arXiv preprint arXiv:2502.06882},
year = {2025}
}