From Query to Counsel: Structured Reasoning with a Multi-Agent Framework and Dataset for Legal Consultation
For legal consultation QA, this work addresses data scarcity and complex reasoning by introducing a structured dataset and modular framework, achieving strong empirical gains over existing models.
The authors constructed JurisCQAD, a dataset of over 43,000 Chinese legal queries with expert-validated responses, and proposed JurisMA, a multi-agent framework for legal consultation QA. Their system significantly outperformed general-purpose and legal-domain LLMs on the refined LawBench benchmark.
Legal consultation question answering (Legal CQA) presents unique challenges compared to traditional legal QA tasks, including the scarcity of high-quality training data, complex task composition, and strong contextual dependencies. To address these, we construct JurisCQAD, a large-scale dataset of over 43,000 real-world Chinese legal queries annotated with expert-validated positive and negative responses, and design a structured task decomposition that converts each query into a legal element graph integrating entities, events, intents, and legal issues. We further propose JurisMA, a modular multi-agent framework supporting dynamic routing, statutory grounding, and stylistic optimization. Combined with the element graph, the framework enables strong context-aware reasoning, effectively capturing dependencies across legal facts, norms, and procedural logic. Trained on JurisCQAD and evaluated on a refined LawBench, our system significantly outperforms both general-purpose and legal-domain LLMs across multiple lexical and semantic metrics, demonstrating the benefits of interpretable decomposition and modular collaboration in Legal CQA.