用多个AI代理模拟法官合议，提升司法决策的透明与公正。
Agents on the Bench: Large Language Model Based Multi Agent Framework for Trustworthy Digital Justice
- 设计多智能体框架，模拟法庭合议过程进行协同决策。
- 在法律判决预测任务中表现优于现有LLM方法，提升决策质量。
- 适合关注司法AI可信性、可解释性的研究者与实践者。
司法系统日益采用AI技术提升效率，但在决策质量方面仍存在局限，尤其缺乏透明度和可解释性，难以维持公众对法律AI的信任。为此，我们提出基于大语言模型的多智能体框架AgentsBench，旨在同时提升司法决策的效率与质量。该方法利用多个由LLM驱动的智能体，模拟法庭合议的协作讨论与决策过程。我们在法律判决预测任务上进行了实验，结果表明，该框架在性能和决策质量上均优于现有基于LLM的方法。通过融入真实司法流程特征，框架显著提升了准确性、公平性与社会考量能力。AgentsBench为可信AI决策提供了更细致、更贴近现实的范式，具备在多种案件类型和法律场景中的广泛应用潜力。
原文摘要 · Abstract (English)
The justice system has increasingly employed AI techniques to enhance efficiency, yet limitations remain in improving the quality of decision-making, particularly regarding transparency and explainability needed to uphold public trust in legal AI. To address these challenges, we propose a large language model based multi-agent framework named AgentsBench, which aims to simultaneously improve both efficiency and quality in judicial decision-making. Our approach leverages multiple LLM-driven agents that simulate the collaborative deliberation and decision making process of a judicial bench. We conducted experiments on legal judgment prediction task, and the results show that our framework outperforms existing LLM based methods in terms of performance and decision quality. By incorporating these elements, our framework reflects real-world judicial processes more closely, enhancing accuracy, fairness, and society consideration. AgentsBench provides a more nuanced and realistic methods of trustworthy AI decision-making, with strong potential for application across various case types and legal scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。