LawThinker: A Deep Research Legal Agent in Dynamic Environments
This addresses the issue of undetected errors in legal reasoning for legal professionals, though it is incremental as it builds on existing verification and memory techniques.
The paper tackles the problem of ensuring procedurally compliant reasoning in legal research by proposing LawThinker, an agent that verifies each step, resulting in a 24% improvement over direct reasoning and 11% over workflow-based methods on a dynamic benchmark.
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 .