VERDICT: 可验证的演进推理与指令驱动的协作团队用于法律判断预测
VERDICT: Verifiable Evolving Reasoning with Directive-Informed Collegial Teams for Legal Judgment Prediction
AI总结：
VERDICT通过模拟虚拟合议庭，提出自反思协作多智能体框架，结合混合法理记忆实现法律推理的可验证性和适应性，提升法律预测的准确性和解释性。
摘要：
法律判断预测（LJP）从案件事实预测适用的法律条文、指控和罚则。除了准确性外，LJP要求内在可解释且法律基础的推理，能够协调法律规则与先例驱动的标准。然而，现有方法通常表现为静态的一次性预测器，提供有限的可验证推理过程支持和很少的适应能力，以应对法律实践的演变。我们提出了VERDICT，一个自反思协作多智能体框架，模拟虚拟合议庭。VERDICT分配专门的智能体到互补的角色（例如，事实结构化、法律检索、意见起草和监督验证），并在可追溯的草拟-验证-修订工作流中协调它们，通过显式的通过/拒绝反馈，产生可验证的推理轨迹和修订理由。为了捕捉演进的案件经验，我们进一步引入基于微指令范式的混合法理记忆（HJM），该记忆存储先例标准，并持续提炼验证的多智能体验证轨迹，将其转化为更新的微指令，以在跨案例中实现持续学习。我们评估VERDICT在CAIL2018和新构建的CJO2025数据集上，采用严格的未来时间分割进行时间泛化。VERDICT在CAIL2018上实现了最先进的性能，并在CJO2025上展示了强大的泛化能力。为促进可重复性和进一步研究，我们发布代码和数据集在https://anonymous.4open.science/r/ARR-4437。
英文摘要：
Legal Judgment Prediction (LJP) predicts applicable law articles, charges, and penalty terms from case facts. Beyond accuracy, LJP calls for intrinsically interpretable and legally grounded reasoning that can reconcile statutory rules with precedent-informed standards. However, existing methods often behave as static, one-shot predictors, providing limited procedural support for verifiable reasoning and little capability to adapt as jurisprudential practice evolves. We propose VERDICT, a self-refining collaborative multi-agent framework that simulates a virtual collegial panel. VERDICT assigns specialized agents to complementary roles (e.g., fact structuring, legal retrieval, opinion drafting, and supervisory verification) and coordinates them in a traceable draft--verify--revise workflow with explicit Pass/Reject feedback, producing verifiable reasoning traces and revision rationales. To capture evolving case experience, we further introduce a Hybrid Jurisprudential Memory (HJM) grounded in the Micro-Directive Paradigm, which stores precedent standards and continually distills validated multi-agent verification trajectories into updated Micro-Directives for continual learning across cases. We evaluate VERDICT on CAIL2018 and a newly constructed CJO2025 dataset with a strict future time-split for temporal generalization. VERDICT achieves state-of-the-art performance on CAIL2018 and demonstrates strong generalization on CJO2025. To facilitate reproducibility and further research, we release our code and the dataset at https://anonymous.4open.science/r/ARR-4437.
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。
