LegalEvolver：基于评分准则自进化的法律判决预测框架
LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution
一篇讲法律检索 Agent 怎么自己变强的论文，用 rubric 迭代做 RL，比固定规则效果好，做法律 AI 或 Agent 训练的可以看看
arXiv 论文 LegalEvolver 针对 LLM Agent 在法律判决预测（LJP）任务中检索质量不佳的问题，提出查询优化框架。它先用启发式方法优化查询作为种子生成检索轨迹，再把 rollout 经验总结成评分准则（rubrics），用于指导多轮迭代自进化。实验显示，rubric 优化配合 rubric-guided RL 让模型超越初始性能上限，且不断进化的 rubrics 优于固定 rubrics，与直接 SFT 加 RL 的路线相比也有优势。
LegalEvolver: Agentic Legal Judgment Prediction via Rubric-Guided Self-Evolution
As LLM-based agents develop, they have been increasingly applied in the legal domain. Legal Judgment Prediction~(LJP) requires models to conduct multi-step reasoning and external legal evidence retrieval. Existing legal search agents' performance is often constrained by the quality of retrieval queries. They often formulate queries directly from the initial user request, overlooking latent legal issues and legally salient details. To address this issue, we propose \emph{LegalEvolver}, a query optimization framework specifically designed to generate legally informative queries for LJP-oriented retrieval. Sampling high-quality optimized queries and their corresponding search trajectories is challenging, as relying solely on unguided high-temperature rollouts is both inefficient and constrained by the model's initial capabilities. We therefore heuristically optimize queries as seeds, improving the efficiency of trajectory generation. Furthermore, we summarize rollout experience into rubrics and use them to guide multi-round iterative self-evolution. Iteratively performing rubric optimization and rubric-guided RL enables the model to surpass its initial performance ceiling. End-to-end performance on extensive benchmarks demonstrates the effectiveness of query optimization on LJP. Comparisons with direct SFT followed by RL demonstrate the effectiveness of rubric guidance. Evolving rubrics further outperform fixed rubrics, confirming the benefits of self-evolution.