Investigating Multi-Agent Deliberation in Law

法律领域中多智能体审议的研究

Abstract: Artificial Intelligence is increasingly applied to the field of law, and has the potential to increase access to justice. One particular movement that is gaining traction is that of agentic AI, wherein AI agents, based on Large Language Models (LLMs) can take autonomous actions. In particular, multi-agent approaches in the legal domain remain largely unexplored.

摘要： 人工智能正日益应用于法律领域，并具有提升司法可及性的潜力。当前一个备受关注的趋势是“智能体AI”（agentic AI），即基于大语言模型（LLMs）的AI智能体能够采取自主行动。特别是在法律领域，多智能体方法的研究目前仍处于探索阶段。

In this paper, we investigate multi-agent deliberation methods for legal reasoning tasks using LLMs. We explore multi-agent deliberation (MAD) and introduce two novel multi-agent frameworks inspired by courtroom procedures and legal argumentation.

在本文中，我们研究了利用大语言模型进行法律推理任务的多智能体审议方法。我们探讨了多智能体审议（MAD），并引入了两种受法庭程序和法律论证启发的创新多智能体框架。

Our experiments on both legal and non-legal benchmarks reveal that multi-agent frameworks achieve comparable overall performance to baseline large language models, but produce significantly distinct answers. Notably, these approaches can successfully solve cases that the baseline fails to address, and vice versa.

我们在法律和非法律基准测试上的实验表明，多智能体框架在整体性能上与基准大语言模型相当，但能产生显著不同的答案。值得注意的是，这些方法能够成功解决基准模型无法处理的案例，反之亦然。

We conduct a qualitative evaluation and highlight scenarios where multi-agent frameworks outperform monolithic approaches. For example, multi-agent approaches appear better suited for answering questions that require critical thinking from multiple perspectives. Our work positions multi-agent systems as a promising direction for AI in the legal domain, while demonstrating the potential of law-inspired multi-agent approaches for deliberation.

我们进行了定性评估，并重点介绍了多智能体框架优于单一模型方法的场景。例如，多智能体方法似乎更适合回答需要从多角度进行批判性思考的问题。我们的研究将多智能体系统定位为法律领域AI的一个有前景的方向，同时也展示了受法律启发的审议型多智能体方法的潜力。