LegalMALR:Multi-Agent Query Understanding and LLM-Based Reranking for Chinese Statute Retrieval

TL;DR

LegalMALR is a novel framework combining multi-agent query reformulation and LLM-based reranking to improve Chinese statute retrieval, especially for complex, implicit legal queries, outperforming existing methods.

Contribution

It introduces a multi-agent query understanding system with reinforcement learning and a large-language-model reranker, enhancing retrieval accuracy for difficult legal queries.

Findings

Outperforms strong RAG baselines on CSAID and STARD datasets.

Effectively handles implicit and multi-issue legal queries.

Demonstrates robustness in out-of-distribution scenarios.

Abstract

Statute retrieval is essential for legal assistance and judicial decision support, yet real-world legal queries are often implicit, multi-issue, and expressed in colloquial or underspecified forms. These characteristics make it difficult for conventional retrieval-augmented generation pipelines to recover the statutory elements required for accurate retrieval. Dense retrievers focus primarily on the literal surface form of the query, whereas lightweight rerankers lack the legal-reasoning capacity needed to assess statutory applicability. We present LegalMALR, a retrieval framework that integrates a Multi-Agent Query Understanding System (MAS) with a zero-shot large-language-model-based reranking module (LLM Reranker). MAS generates diverse, legally grounded reformulations and conducts iterative dense retrieval to broaden candidate coverage. To stabilise the stochastic behaviour of LLM-generated rewrites, we optimise a unified MAS policy using Generalized Reinforcement Policy Optimization(GRPO). The accumulated candidate set is subsequently evaluated by the LLM Reranker, which performs natural-language legal reasoning to produce the final ranking. We further construct CSAID, a dataset of 118 difficult Chinese legal queries annotated with multiple statutory labels, and evaluate LegalMALR on both CSAID and the public STARD benchmark. Experiments show that LegalMALR substantially outperforms strong Retrieval-augmented generation(RAG) baselines in both in-distribution and out-of-distribution settings, demonstrating the effectiveness of combining multi-perspective query interpretation, reinforcement-based policy optimisation, and large-model reranking for statute retrieval.