When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval
Quick Answer
This study introduces a self-evolving framework for legal case retrieval that enhances BM25 without parameter training.
Quick Take
This study introduces a self-evolving framework for legal case retrieval that enhances BM25 without parameter training. Using an LLM-based agent, it iteratively refines query rewriting rules, outperforming traditional methods on the LeCaRD-v2 benchmark. The findings highlight the importance of leveraging historical feedback and LLM capabilities in optimizing rule sets.
Key Points
- Proposed a self-evolving framework for legal case retrieval enhancing BM25.
- Framework uses an LLM-based agent for iterative rule rewriting without training.
- Outperformed human-designed rules and greedy selection on LeCaRD-v2 benchmark.
- Highlights LLM's role in leveraging historical feedback for rule refinement.
- Demonstrates significant improvements in legal query retrieval efficiency.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 17220v1 Announce Type: new 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 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.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Arbor: Tree Search as a Cognition Layer for Autonomous Agents
Arbor introduces a multi-agent framework utilizing structured tree search for optimizing LLM inference, achieving up to 193% throughput-latency improvement compared to vendor-optimized systems. It employs an Orchestrator and Critic agent for stability and coordination, demonstrating hardware-agnostic performance with minimal variance.