Problem
Research questions and friction points this paper is trying to address.
Legal QA
Deep Research
Evidence-grounded
Multi-step Reasoning
Retrieval-Augmented Generation
LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence
🤖 AI Summary
Existing legal AI systems are largely confined to simple question-answering, struggling with complex tasks requiring systematic evidence retrieval and multi-step reasoning. This work proposes an evidence-oriented legal research assistant that integrates large language models, retrieval-augmented generation (RAG), and query rewriting techniques. The system comprises three core modules—precise question-answering, structured retrieval, and multi-agent deep research—facilitating a paradigm shift from conversational QA to multi-agent collaboration. Explicit citations are maintained throughout the entire pipeline to support traceability and verification. By delivering verifiable legal research reports, this study establishes a practical paradigm for transforming conversational AI into trustworthy, scalable, evidence-driven legal assistants.
📝 Abstract
Recent advances in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have significantly democratized access to legal information. Nevertheless, most existing legal assistants remain confined to multi-turn conversational QA, failing to support complex legal tasks that require systematic evidence retrieval, multi-step reasoning, and report-level synthesis. In this paper, we present LawCompass, an evidence-grounded legal assistant that navigates the transition from standard Legal QA to multi-agent deep research. LawCompass provides three task-oriented functions: Legal QA, which delivers precise, evidence-backed answers to legal questions; Professional Retrieval, which enables structured exploration of statutes and judicial cases via query rewriting; and Deep Research, which employs a multi-agent workflow to decompose complex legal tasks and synthesize comprehensive research reports. Crucially, LawCompass maintains explicit citation links across all modules, empowering users to directly verify system outputs against original legal sources. Evaluation results demonstrate that LawCompass provides a practical and scalable paradigm for transforming conversational AI into trustworthy and evidence-grounded legal research assistance.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Multi-Agent Deep Research
Retrieval-Augmented Generation
Evidence-Grounded
Legal QA
Query Rewriting
🔎 Similar Papers
No similar papers found.
