Search papers, labs, and topics across Lattice.
The paper introduces LawThinker, a legal reasoning agent designed to improve the accuracy and procedural compliance of legal reasoning in dynamic judicial environments. LawThinker employs an "Explore-Verify-Memorize" strategy, using a DeepVerifier module to assess retrieved knowledge for accuracy, relevance, and compliance after each exploration step. Experiments on the J1-EVAL benchmark demonstrate that LawThinker significantly outperforms existing methods, achieving a 24% improvement over direct reasoning and an 11% gain over workflow-based approaches, while also generalizing effectively to static benchmarks.
LawThinker's "Explore-Verify-Memorize" strategy enforces verification as an atomic operation, leading to a 24% performance boost in dynamic legal reasoning environments compared to direct reasoning.
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 .
