# LawThinker: A Deep Research Legal Agent in Dynamic Environments

arXiv: https://arxiv.org/abs/2602.12056 · HTML: https://mlsanity.com/paper/2602.12056/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 28 of its 55 references that are in the map.
- First posted on arXiv 12 Feb 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 28 of 28)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools](https://mlsanity.com/paper/2406.12793/) (2024)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems](https://mlsanity.com/paper/2508.07407/) (2025)
- [Qwen2.5-1M Technical Report](https://mlsanity.com/paper/2501.15383/) (2025)
- [DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services](https://mlsanity.com/paper/2309.11325/) (2023)
- [SAILER: Structure-aware Pre-trained Language Model for Legal Case Retrieval](https://mlsanity.com/paper/2304.11370/) (2023)
- [Efficient Inference for Large Reasoning Models: A Survey](https://mlsanity.com/paper/2503.23077/) (2025)
- [LegalAgentBench: Evaluating LLM Agents in Legal Domain](https://mlsanity.com/paper/2412.17259/) (2024)
- [MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning](https://mlsanity.com/paper/2507.16812/) (2025)
- [Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration](https://mlsanity.com/paper/2310.09241/) (2023)
- [A Survey on Large Language Models for Mathematical Reasoning](https://mlsanity.com/paper/2506.08446/) (2025)
- [Legal Syllogism Prompting: Teaching Large Language Models for Legal Judgment Prediction](https://mlsanity.com/paper/2307.08321/) (2023)
- [Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning](https://mlsanity.com/paper/2502.02871/) (2025)
- [LLMs Provide Unstable Answers to Legal Questions](https://mlsanity.com/paper/2502.05196/) (2025)
- [Enhancing Code Generation Performance of Smaller Models by Distilling the Reasoning Ability of LLMs](https://mlsanity.com/paper/2403.13271/) (2024)
- [Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction](https://mlsanity.com/paper/2407.01964/) (2024)
- [Ready Jurist One: Benchmarking Language Agents for Legal Intelligence in Dynamic Environments](https://mlsanity.com/paper/2507.04037/) (2025)
- [L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit](https://mlsanity.com/paper/2509.00761/) (2025)
- [Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond](https://mlsanity.com/paper/2503.16040/) (2025)
- [LRAS: Advanced Legal Reasoning with Agentic Search](https://mlsanity.com/paper/2601.07296/) (2026)
- [GLARE: Agentic Reasoning for Legal Judgment Prediction](https://mlsanity.com/paper/2508.16383/) (2025)
- [A Study on Thinking Patterns of Large Reasoning Models in Code Generation](https://mlsanity.com/paper/2509.13758/) (2025)
- [MASLegalBench: Benchmarking Multi-Agent Systems in Deductive Legal Reasoning](https://mlsanity.com/paper/2509.24922/) (2025)

## Built on by (most cited first, 4 of 4)

- [Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering](https://mlsanity.com/paper/2605.29742/) (2026)
- [NyayaMind- A Framework for Transparent Legal Reasoning and Judgment Prediction in the Indian Legal System](https://mlsanity.com/paper/2604.09069/) (2026)
- [LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents](https://mlsanity.com/paper/2609.09754/) (2026)
- [Test-Time Agent Evolution for Long-Horizon Legal Reasoning](https://mlsanity.com/paper/2610.08138/) (2026)

## Abstract (arXiv)

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 .