Legal-R1: Agentic Retrieval for Evidence-Based Legal Reasoning

arXiv:2610.18611 · cs.CL · Submitted 2026-10-13 · Read on arXiv

cs.CL

Submitted: 2026-10-13

Updated: 2026-10-13

Code: https://github.com/killerqueen-wonder/Legal-R1

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Agentic Retrieval — 1× in this paper

Sources

• Training Verifiers to Solve Math Word Problems
• Retrieval-Augmented Generation for Large Language Models: A Survey
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Measuring Mathematical Problem Solving With the MATH Dataset
• LegalOne: A Family of Foundation Models for Reliable Legal Reasoning
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• WisdomInterrogatory (LuWen): An Open-Source Legal Large Language Model Technical Report
• CAIL2018: A Large-Scale Legal Dataset for Judgment Prediction
• Benchmark Data Contamination of Large Language Models: A Survey
• ReAct: Synergizing Reasoning and Acting in Language Models
• DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
• A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning
• R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learning
• LawGPT: A Chinese Legal Knowledge-Enhanced Large Language Model

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering