LawThinker: A Deep Research Legal Agent in Dynamic Environments

TL;DR

LawThinker is an autonomous legal research agent that enhances reasoning accuracy and procedural compliance in dynamic judicial environments through a verification-driven, memory-augmented approach, significantly improving performance on benchmark tasks.

Contribution

It introduces LawThinker, a novel legal reasoning framework that incorporates verification after each knowledge exploration step and a memory module for improved accuracy and compliance.

Findings

24% improvement over direct reasoning on J1-EVAL

11% gain over workflow-based methods

Strong generalization on static benchmarks

Abstract

Legal reasoning requires not only correct outcomes but also procedurally compliant reasoning processes. However, existing methods lack mechanisms to verify intermediate reasoning steps, allowing errors such as inapplicable statute citations to propagate undetected through the reasoning chain. To address this, we propose LawThinker, an autonomous legal research agent that adopts an Explore-Verify-Memorize strategy for dynamic judicial environments. The core idea is to enforce verification as an atomic operation after every knowledge exploration step. A DeepVerifier module examines each retrieval result along three dimensions of knowledge accuracy, fact-law relevance, and procedural compliance, with a memory module for cross-round knowledge reuse in long-horizon tasks. Experiments on the dynamic benchmark J1-EVAL show that LawThinker achieves a 24% improvement over direct reasoning and an 11% gain over workflow-based methods, with particularly strong improvements on process-oriented metrics. Evaluations on three static benchmarks further confirm its generalization capability. The code is available at https://github.com/yxy-919/LawThinker-agent .