mlsanityData to 14 Oct 2026

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

arXiv 2610.18611 ↗First posted 13 Oct 2026cs.CLcited by 0

On the map: Retrieval-augmented generation → Legal and financial RAG also fits: Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

Legal question answering requires answers that are not only plausible, but also grounded in legally valid and citable evidence. Standard retrieval-augmented generation often relies on one-shot semantic matching, which is insufficient when legal evidence must be selected according to authority, applicability, and diversity across heterogeneous sources. We introduce Legal-R1, an agentic retrieval framework for evidence-based legal reasoning. Legal-R1 decomposes legal reasoning into a multi-agent workflow, where a Lawyer agent learns when to retrieve, which legal source to query, what evidence to seek, and when the collected evidence is sufficient. A Legal Assistant agent retrieves from normative legal sources and precedent cases with authority-aware and diversity-aware selection, while a Judge agent generates the final answer from the complete evidence trajectory. We post-train only the Lawyer agent with masked supervised fine-tuning and trajectory-aware reinforcement learning. Experiments on multiple Chinese legal benchmarks show that Legal-R1 improves over general-purpose, legal-specific, and retrieval-augmented baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 28 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

13 of 28 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024CBR-RAG: Case-Based Reasoning for Retrieval Augmented Generation in LLMs for Legal Question Answering4 Apr

Other references · 12

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  6. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  7. 2022Self-Instruct: Aligning Language Models with Self-Generated Instructionscited by 2,724
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  9. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  10. 2018CAIL2018: A Large-Scale Legal Dataset for Judgment Predictioncited by 170
  11. 2023LeCaRDv2: A Large-Scale Chinese Legal Case Retrieval Datasetcited by 38
  12. 2025R-Search: Empowering LLM Reasoning with Search via Multi-Reward Reinforcement Learningcited by 34

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LawCompass: Navigating from Legal QA to Multi-Agent Deep Research with Grounded Evidence
  2. 2025Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
  3. 2025L-MARS: Legal Multi-Agent System with Agentic Search and Citation-Faithfulness Audit
  4. 2026LRAS: Advanced Legal Reasoning with Agentic Search
  5. 2025A Reasoning-Focused Legal Retrieval Benchmark
  6. 2026LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
  7. 2026When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval
  8. 2026LegalMALR:Multi-Agent Query Understanding and LLM-Based Reranking for Chinese Statute Retrieval