When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval

当规则学会学习：一种用于法律案例检索的自进化智能体

Abstract: Legal case retrieval remains challenging due to the complexity of legal language and the need for precise lexical alignment between queries and relevant cases. Although dense retrieval models have achieved notable progress, empirical studies show that BM25 continues to serve as a strong baseline in this domain.

摘要： 由于法律语言的复杂性以及查询与相关案例之间需要精确的词汇对齐，法律案例检索仍然是一项具有挑战性的任务。尽管稠密检索模型（Dense Retrieval Models）已经取得了显著进展，但实证研究表明，BM25 在该领域仍然是一个强有力的基准。

It motivates us to propose a self-evolving framework for rule-driven query rewriting that enhances BM25 without any parameter training. The framework equips an LLM-based agent with an automatic evaluation environment, enabling it to iteratively create rewriting rules, plan validation experiments over rule combinations, and eliminate ineffective rules based on historical feedbacks.

这促使我们提出了一种用于规则驱动查询重写的自进化框架，该框架无需任何参数训练即可增强 BM25。该框架为基于大语言模型（LLM）的智能体配备了一个自动评估环境，使其能够迭代地创建重写规则、规划规则组合的验证实验，并根据历史反馈剔除无效规则。

We evaluate our method on the Chinese legal case retrieval benchmark LeCaRD-v2. Experimental results demonstrate that the proposed framework outperforms non-evolutionary baselines, including human-designed rules and greedy rule selection, particularly when powered by a high-capacity core LLM.

我们在中文法律案例检索基准 LeCaRD-v2 上评估了我们的方法。实验结果表明，该框架优于非进化基准（包括人工设计的规则和贪婪规则选择），特别是在由高容量核心大模型驱动时表现尤为突出。

We also conduct detailed analyses to investigate the mechanisms underlying self-evolution. Our findings reveal that LLM’s capabilities to leverage previous experimental results and its intrinsic knowledge of rule elimination play critical roles in refining the rule set via self-evolution.

我们还进行了详细的分析，以探究自进化背后的机制。研究结果表明，大模型利用过往实验结果的能力及其在规则剔除方面的内在知识，在通过自进化优化规则集的过程中发挥了关键作用。