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

arXiv: https://arxiv.org/abs/2606.17220 · HTML: https://mlsanity.com/paper/2606.17220/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use.
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Placed in

- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)
- Synthetic data and self-improvement for LLMs / [Self-evolving search agents](https://mlsanity.com/synth/self-evolving-search-agents/)

## Builds on (most cited first, 9 of 9)

- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [AgentEvolver: Towards Efficient Self-Evolving Agent System](https://mlsanity.com/paper/2511.10395/) (2025)
- [SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval](https://mlsanity.com/paper/2304.11370/) (2023)
- [EvolveSearch: An Iterative Self-Evolving Search Agent](https://mlsanity.com/paper/2505.22501/) (2025)
- [LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Dataset](https://mlsanity.com/paper/2310.17609/) (2023)
- [Yes, BM25 is a Strong Baseline for Legal Case Retrieval](https://mlsanity.com/paper/2105.05686/) (2021)
- [ELLA: Empowering LLMs for Interpretable, Accurate and Informative Legal Advice](https://mlsanity.com/paper/2408.07137/) (2024)
- [ReaKase-8B: Legal Case Retrieval via Knowledge and Reasoning Representations with LLMs](https://mlsanity.com/paper/2510.26178/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Existing Methods to New Research Ideas: Two Perspectives on Recursive Self-Improvement](https://mlsanity.com/paper/2610.14625/) (2026)

## Abstract (arXiv)

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 create rewriting rules, plan validation experiments over rule combinations, and 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 highcapacity 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.