LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning

2026-05-27

AI Summary

Existing legal reasoning approaches struggle to structure heterogeneous legal texts and lack mechanisms for evidence verification, resulting in unreliable and opaque inference. This work proposes a GraphRAG framework that integrates a hierarchical legal knowledge graph with a multi-agent collaborative verification system. The knowledge graph enables multi-granularity retrieval, while the multi-agent component—comprising researcher, auditor, and adjudicator agents—facilitates evidence retrieval, validation, and synthetic judgment. This approach establishes, for the first time in the legal domain, a verifiable and interpretable reasoning chain. Experimental results demonstrate that the proposed method significantly outperforms existing GraphRAG baselines across multiple legal analysis tasks, effectively enhancing both reasoning accuracy and trustworthiness.

Abstract

Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more coherent and effective reasoning. However, applying it to specific domains like legal reasoning faces critical challenges. (i) Legal corpora are heterogeneous, containing multi-granular knowledge from cases, articles and interpretations. A flat knowledge graph cannot adequately differentiate between factual details, applied rules, and abstract principles, limiting accurate retrieval. (ii) Reliable legal judgment demands transparent, evidence-based reasoning. Traditional RAG passes retrieved context directly to an LLM without verification, resulting in opaque, error-prone reasoning. To this end, we propose LegalGraphRAG, a framework designed for reliable legal reasoning. Our approach introduces two core components: a hierarchical legal graph that hierarchically organizes legal sources to enable retrieval at appropriate abstraction levels, and a multi-agent system for reliable legal reasoning, where a Researcher retrieves candidate evidence, an Auditor rigorously verifies its validity against source documents, and an Adjudicator synthesizes the set of verified evidence to render a final judgment. Extensive experiments show that LegalGraphRAG achieves the state-of-the-art performance, outperforming existing GraphRAG baselines in accurate and trustworthy legal analysis. Our code, datasets and implementation details are available at https://github.com/XMUDeepLIT/LegalGraphRAG.

Problem

• Legal Reasoning
• Graph Retrieval-Augmented Generation
• Heterogeneous Legal Corpora
• Transparent Reasoning
• Knowledge Graph

Innovation

• GraphRAG
• legal reasoning
• hierarchical knowledge graph
• multi-agent system
• retrieval-augmented generation