arXiv 2408.080892025-06-16cs.CLcs.AI

AgentCourt：利用对抗性可演化律师智能体模拟法庭

AgentCourt: Simulating Court with Adversarial Evolvable Lawyer Agents

Southern University of Science and Technology（南方科技大学）；Shenzhen Key Laboratory for High Performance Data Mining, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（深圳高性能数据挖掘重点实验室，深圳先进技术研究所，中国科学院）；SIAT-DELI AI and Law Joint Lab（SIAT-DELI人工智能与法律联合实验室）；Shenzhen MSU-BIT University（深圳MSU-BIT大学）；UNSW Sydney（新南威尔士大学悉尼分校）；SUAT（南方科技大学）

Guhong Chen, Liyang Fan, Zihan Gong, Nan Xie, Zixuan Li, Ziqiang Liu, Chengming Li, Qiang Qu, Hamid Alinejad-Rokny, Shiwen Ni, Min Yang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对现有法律AI难以应对动态法庭互动的问题，研究提出AgentCourt法律模拟框架及AdvEvol对抗演化方法，通过模拟千起民事案件演化律师智能体，在CourtBench基准上性能提升12.1%，获专业律师认可，为法律AI发展提供新方向。

摘要：

当前基于大语言模型（LLM）的模拟系统研究缺乏建模真实法庭诉讼程序的综合解决方案，而现有法律语言模型在应对动态法庭互动方面存在困难。我们提出了AgentCourt，这是一个综合性法律模拟框架，通过基于LLM的智能体的对抗演化来解决这些挑战。我们的AgentCourt引入了一种名为AdvEvol的新型智能体对抗演化方法，它在模拟法庭程序中通过结构化对抗互动进行动态知识学习与演化，打破了传统依赖静态知识库或人工标注的局限性。通过模拟1000起民事案件，我们构建了一个不断演化的知识库，提升了智能体的法律推理能力。演化后的律师智能体在我们新推出的CourtBench基准上表现出色，与原始律师智能体相比性能提升了12.1%。专业律师的评估证实了我们的方法在认知敏捷性、专业知识和逻辑严谨性三个关键维度上的有效性。除了在交互式推理任务中优于专门的法律模型外，我们的研究结果强调了对抗学习在法律人工智能中的重要性，并为将基于模拟的法律推理拓展到更广泛的司法和监管场景指明了有前景的方向。项目代码可在以下网址获取：https://github.com/relic-yuexi/AgentCourt

英文摘要：

Current research in LLM-based simulation systems lacks comprehensive solutions for modeling real-world court proceedings, while existing legal language models struggle with dynamic courtroom interactions. We present AgentCourt, a comprehensive legal simulation framework that addresses these challenges through adversarial evolution of LLM-based agents. Our AgentCourt introduces a new adversarial evolutionary approach for agents called AdvEvol, which performs dynamic knowledge learning and evolution through structured adversarial interactions in a simulated courtroom program, breaking the limitations of the traditional reliance on static knowledge bases or manual annotations. By simulating 1,000 civil cases, we construct an evolving knowledge base that enhances the agents' legal reasoning abilities. The evolved lawyer agents demonstrated outstanding performance on our newly introduced CourtBench benchmark, achieving a 12.1% improvement in performance compared to the original lawyer agents. Evaluations by professional lawyers confirm the effectiveness of our approach across three critical dimensions: cognitive agility, professional knowledge, and logical rigor. Beyond outperforming specialized legal models in interactive reasoning tasks, our findings emphasize the importance of adversarial learning in legal AI and suggest promising directions for extending simulation-based legal reasoning to broader judicial and regulatory contexts. The project's code is available at: https://github.com/relic-yuexi/AgentCourt

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。