@inproceedings{tao-etal-2026-rules,
    title = "When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval",
    author = "Tao, Mingxu  and
      Hu, Jiawei  and
      Zhou, Xian  and
      Hu, Wenpeng  and
      Cheng, Jiajun  and
      Cao, Yunbo  and
      Luo, Zhunchen  and
      Geng, Guotong",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.2152/",
    pages = "43348--43365",
    ISBN = "979-8-89176-395-1",
    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. 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 \textbf{create rewriting rules}, \textbf{plan validation experiments} over rule combinations, and \textbf{eliminate ineffective rules} based on historical feedbacks. 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. 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."
}