mlsanityData to 14 Oct 2026

Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning

arXiv 2502.19655 ↗First posted 27 Feb 2025cs.CL cs.AIcited by 40

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

Reinforcement learning from verifiable rewards (RLVR) has recently gained attention for its ability to elicit self-evolved reasoning capabilitie from base language models without explicit reasoning supervisions, as demonstrated by DeepSeek-R1. While prior work on RLVR has primarily focused on mathematical and coding domains, its applicability to other tasks and domains remains unexplored. In this work, we investigate whether medical reasoning can emerge from RLVR. We introduce Med-RLVR as an initial study of RLVR in the medical domain leveraging medical multiple-choice question answering (MCQA) data as verifiable labels. Our results demonstrate that RLVR is not only effective for math and coding but also extends successfully to medical question answering. Notably, Med-RLVR achieves performance comparable to traditional supervised fine-tuning (SFT) on in-distribution tasks while significantly improving out-of-distribution generalization, with an 8-point accuracy gain. Further analysis of training dynamics reveals that, with no explicit reasoning supervision, reasoning emerges from the 3B-parameter base model. These findings underscore the potential of RLVR in domains beyond math and coding, opening new avenues for its application in knowledge-intensive fields such as medicine.

Key facts. Cited by 40 papers in the map (data through 14 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 11 of its 14 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

11 of 14 references.

References · 11

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2023Let's Verify Step by Stepcited by 3,789
  4. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  5. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  6. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  7. 2020What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Examscited by 1,356
  8. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  9. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 672
  10. 2023Can Generalist Foundation Models Outcompete Special-Purpose Tuning? Case Study in Medicinecited by 329
  11. 2025Demystifying Long Chain-of-Thought Reasoning in LLMscited by 326

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 28; 2026: 12.

40 papers.

Sort:

By area:

  1. 2025Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domainscited by 366
  2. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  3. 2025The Invisible Leash: Why RLVR May or May Not Escape Its Origincited by 97
  4. 2025A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibilitycited by 93
  5. 2025Online Rubrics Elicitation from Pairwise Comparisonscited by 46
  6. 2025QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Trainingcited by 38
  7. 2025X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domainscited by 31
  8. 2025ReasonMap: Towards Fine-Grained Visual Reasoning from Transit Mapscited by 23
  9. 2025MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Sciencecited by 23
  10. 2025BLEUBERI: BLEU is a surprisingly effective reward for instruction followingcited by 17
  11. 2025Reinforcement Learning vs. Distillation: Understanding Accuracy and Capability in LLM Reasoningcited by 14
  12. 2025Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learningcited by 14
28 more
  1. 2025OralGPT-Omni: A Versatile Dental Multimodal Large Language Modelcited by 11
  2. 2025Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applicationscited by 10
  3. 2025Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learningcited by 10
  4. 2025OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoningcited by 10
  5. 2025Can Large Language Models Develop Strategic Reasoning? Post-training Insights from Learning Chesscited by 9
  6. 2025Reasoning BO: Enhancing Bayesian Optimization with Long-Context Reasoning Power of LLMscited by 8
  7. 2025Med-U1: Incentivizing Unified Medical Reasoning in LLMs via Large-scale Reinforcement Learningcited by 8
  8. 2026MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learningcited by 8
  9. 2025Open-Medical-R1: How to Choose Data for RLVR Training at Medicine Domaincited by 7
  10. 2025DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistrycited by 6
  11. 2026Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoningcited by 5
  12. 2025Training and Evaluation of Guideline-Based Medical Reasoning in LLMscited by 4
  13. 2025Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained Reflectioncited by 3
  14. 2026When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gainscited by 3
  15. 2025Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMscited by 2
  16. 2025One Patient, Many Contexts: Scaling Medical AI with Contextual Intelligencecited by 2
  17. 2025RLoop: An Self-Improving Framework for Reinforcement Learning with Iterative Policy Initializationcited by 2
  18. 2026LLMs can construct powerful representations and streamline sample-efficient supervised learningcited by 2
  19. 2025Pedagogy-R1: Pedagogically-Aligned Reasoning Model with Balanced Educational Benchmarkcited by 1
  20. 2026Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentationcited by 1
  21. 2026Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Designcited by 1
  22. 2026Process Reward Agents for Steering Knowledge-Intensive Reasoningcited by 1
  23. 2025Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patientscited by 0
  24. 2026Infection-Reasoner: A Compact Vision-Language Model for Wound Infection Classification with Evidence-Grounded Clinical Reasoningcited by 0
  25. 2026Trading Human Curation for Synthetic Augmentation in RLVRcited by 0
  26. 2026RareDxR1: Autonomous Medical Reasoning for Rare Disease Diagnosis Beyond Human Annotationcited by 0
  27. 2026Reinforcement Learning for Evidence-Seeking Diagnostic Reasoning with Large Language Modelscited by 0
  28. 2026Reasoning Before Translation: Enhancing Legal Machine Translation with Structured Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MedVLThinker: Simple Baselines for Multimodal Medical Reasoning
  2. 2025Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation
  3. 2025GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning
  4. 2025Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
  5. 2025Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL
  6. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
  7. 2025Med-R3: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning
  8. 2025CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making