# LRAS: Advanced Legal Reasoning with Agentic Search

arXiv: https://arxiv.org/abs/2601.07296 · HTML: https://mlsanity.com/paper/2601.07296/

## Key facts

- Cited by 8 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 16 of its 31 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)
- LLM agents and tool use / [Social simulation and multi-agent debate](https://mlsanity.com/agents/social-simulation-and-multi-agent-debate/)

## Builds on (most cited first, 16 of 16)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction](https://mlsanity.com/paper/1807.02478/) (2018)
- [DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services](https://mlsanity.com/paper/2309.11325/) (2023)
- [Fine-tuning Large Language Models for Improving Factuality in Legal Question Answering](https://mlsanity.com/paper/2501.06521/) (2025)
- [LLMs Provide Unstable Answers to Legal Questions](https://mlsanity.com/paper/2502.05196/) (2025)
- [LegalDelta: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain](https://mlsanity.com/paper/2508.12281/) (2025)
- [Large Language Models Meet Legal Artificial Intelligence: A Survey](https://mlsanity.com/paper/2509.09969/) (2025)
- [LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning](https://mlsanity.com/paper/2506.07443/) (2025)
- [Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving](https://mlsanity.com/paper/2506.17104/) (2025)
- [Legal Mathematical Reasoning with LLMs: Procedural Alignment through Two-Stage Reinforcement Learning](https://mlsanity.com/paper/2504.02590/) (2025)
- [Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization](https://mlsanity.com/paper/2510.11184/) (2025)
- [GLARE: Agentic Reasoning for Legal Judgment Prediction](https://mlsanity.com/paper/2508.16383/) (2025)
- [LexChain: Modeling Legal Reasoning Chains for Chinese Tort Case Analysis](https://mlsanity.com/paper/2510.17602/) (2025)
- [Can Group Relative Policy Optimization Improve Thai Legal Reasoning and Question Answering?](https://mlsanity.com/paper/2507.09638/) (2025)

## Built on by (most cited first, 8 of 8)

- [Adaptive Information Control for Search-Augmented LLM Reasoning](https://mlsanity.com/paper/2602.01672/) (2026)
- [SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent](https://mlsanity.com/paper/2608.07449/) (2026)
- [Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification](https://mlsanity.com/paper/2601.22642/) (2026)
- [LawThinker: A Deep Research Legal Agent in Dynamic Environments](https://mlsanity.com/paper/2602.12056/) (2026)
- [SIGHT: Reinforcement Learning with Self-Evidence and Information-Gain Diverse Branching for Search Agent](https://mlsanity.com/paper/2602.11551/) (2026)
- [Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning](https://mlsanity.com/paper/2605.25920/) (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)

## Abstract (arXiv)

While Large Reasoning Models (LRMs) have demonstrated exceptional logical capabilities in mathematical domains, their application to the legal field remains hindered by the strict requirements for procedural rigor and adherence to legal logic. Existing legal LLMs, which rely on "closed-loop reasoning" derived solely from internal parametric knowledge, frequently suffer from lack of self-awareness regarding their knowledge boundaries, leading to confident yet incorrect conclusions. To address this challenge, we present Legal Reasoning with Agentic Search (LRAS), the first framework designed to transition legal LLMs from static and parametric "closed-loop thinking" to dynamic and interactive "Active Inquiry". By integrating Introspective Imitation Learning and Difficulty-aware Reinforcement Learning, LRAS enables LRMs to identify knowledge boundaries and handle legal reasoning complexity. Empirical results demonstrate that LRAS outperforms state-of-the-art baselines by 8.2-32%, with the most substantial gains observed in tasks requiring deep reasoning with reliable knowledge. We will release our data and models for further exploration soon.