mlsanityData to 7 Oct 2026

MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning

arXiv 2502.19634 ↗First posted 26 Feb 2025cs.CV cs.AIcited by 172

On the map: LLM reasoning → Clinical and biomedical applications

also in 1 more
Abstract (arXiv)

Reasoning is a critical frontier for advancing medical image analysis, where transparency and trustworthiness play a central role in both clinician trust and regulatory approval. Although Medical Visual Language Models (VLMs) show promise for radiological tasks, most existing VLMs merely produce final answers without revealing the underlying reasoning. To address this gap, we introduce MedVLM-R1, a medical VLM that explicitly generates natural language reasoning to enhance transparency and trustworthiness. Instead of relying on supervised fine-tuning (SFT), which often suffers from overfitting to training distributions and fails to foster genuine reasoning, MedVLM-R1 employs a reinforcement learning framework that incentivizes the model to discover human-interpretable reasoning paths without using any reasoning references. Despite limited training data (600 visual question answering samples) and model parameters (2B), MedVLM-R1 boosts accuracy from 55.11% to 78.22% across MRI, CT, and X-ray benchmarks, outperforming larger models trained on over a million samples. It also demonstrates robust domain generalization under out-of-distribution tasks. By unifying medical image analysis with explicit reasoning, MedVLM-R1 marks a pivotal step toward trustworthy and interpretable AI in clinical practice. Inference model is available at: https://huggingface.co/JZPeterPan/MedVLM-R1.

Key facts. Cited by 172 papers in the map (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. Builds on 27 of its 35 references that are in the map. First posted on arXiv 26 Feb 2025.

Builds on

27 of 35 references.

References · 27

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  5. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  6. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  7. 2024GPT-4o System Cardcited by 4,467
  8. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  9. 2017Deep reinforcement learning from human preferencescited by 3,846
  10. 2023Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyondcited by 2,179
  11. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  12. 2023LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Daycited by 1,287
15 more
  1. 2022Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Taskscited by 1,057
  2. 2025SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-trainingcited by 655
  3. 2020PathVQA: 30000+ Questions for Medical Visual Question Answeringcited by 467
  4. 2021SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answeringcited by 444
  5. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 405
  6. 2023PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answeringcited by 333
  7. 2023BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Taskscited by 201
  8. 2024HuatuoGPT-Vision, Towards Injecting Medical Visual Knowledge into Multimodal LLMs at Scalecited by 194
  9. 2024OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLMcited by 182
  10. 2023Towards Generalist Foundation Model for Radiology by Leveraging Web-scale 2D&3D Medical Datacited by 176
  11. 2023Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Stepcited by 144
  12. 2024Vision-Language Models for Medical Report Generation and Visual Question Answering: A Reviewcited by 121
  13. 2024Towards a clinically accessible radiology foundation model: open-access and lightweight, with automated evaluationcited by 51
  14. 2024Less Could Be Better: Parameter-efficient Fine-tuning Advances Medical Vision Foundation Modelscited by 17
  15. 2024Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Modelscited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 102; 2026: 70.

172 papers.

Sort:

By area:

  1. 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoningcited by 540
  2. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
  3. 2025Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoningcited by 217
  4. 2025Multimodal Chain-of-Thought Reasoning: A Comprehensive Surveycited by 176
  5. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  6. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Modelscited by 144
  7. 2025Q-Insight: Understanding Image Quality via Visual Reinforcement Learningcited by 93
  8. 2025Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Modelscited by 92
  9. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 89
  10. 2025Patho-R1: A Multimodal Reinforcement Learning-Based Pathology Expert Reasonercited by 38
  11. 2025QoQ-Med: Building Multimodal Clinical Foundation Models with Domain-Aware GRPO Trainingcited by 38
  12. 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoningcited by 37
38 more
  1. 2025Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RLcited by 34
  2. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 34
  3. 2025MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoningcited by 33
  4. 2025ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verificationcited by 30
  5. 2025X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domainscited by 30
  6. 2025Real-World Doctor Agent with Proactive Consultation through Multi-Agent Reinforcement Learningcited by 26
  7. 2025MedVLThinker: Simple Baselines for Multimodal Medical Reasoningcited by 26
  8. 2025Affordance-R1: Reinforcement Learning for Generalizable Affordance Reasoning in Multimodal Large Language Modelcited by 21
  9. 2025Plan-R1: Safe and Feasible Trajectory Planning as Language Modelingcited by 19
  10. 2025Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learningcited by 19
  11. 2025Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessmentcited by 18
  12. 2025UGC-VideoCaptioner: An Omni UGC Video Detail Caption Model and New Benchmarkscited by 17
  13. 2025Improving Medical Reasoning with Curriculum-Aware Reinforcement Learningcited by 16
  14. 2025Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Searchcited by 16
  15. 2025Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysiscited by 16
  16. 2025CrowdVLM-R1: Expanding R1 Ability to Vision Language Model for Crowd Counting using Fuzzy Group Relative Policy Rewardcited by 15
  17. 2025ComfyUI-R1: Exploring Reasoning Models for Workflow Generationcited by 15
  18. 2025Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learningcited by 14
  19. 2025Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessmentcited by 14
  20. 2025Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Modelscited by 13
  21. 2025LLaDA-MedV: Exploring Large Language Diffusion Models for Biomedical Image Understandingcited by 12
  22. 2025Think Twice to See More: Iterative Visual Reasoning in Medical VLMscited by 12
  23. 2026MedMO: Grounding and Understanding Multimodal Large Language Model for Medical Imagescited by 12
  24. 2026MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolutioncited by 12
  25. 2025EgoVLM: Policy Optimization for Egocentric Video Understandingcited by 11
  26. 2025DIP-R1: Deep Inspection and Perception with RL Looking Through and Understanding Complex Scenescited by 10
  27. 2025Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applicationscited by 10
  28. 2025OralGPT-Omni: A Versatile Dental Multimodal Large Language Modelcited by 10
  29. 2025OctoMed: Data Recipes for State-of-the-Art Multimodal Medical Reasoningcited by 10
  30. 2025RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraintscited by 9
  31. 2025Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMscited by 9
  32. 2025Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learningcited by 9
  33. 2026OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysiscited by 9
  34. 2025PathVLM-R1: A Reinforcement Learning-Driven Reasoning Model for Pathology Visual-Language Taskscited by 8
  35. 2025AOR: Anatomical Ontology-Guided Reasoning for Medical Large Multimodal Model in Chest X-Ray Interpretationcited by 8
  36. 2025PRS-Med: Position Reasoning Segmentation in Medical Imagingcited by 8
  37. 2025Behavior Injection: Preparing Language Models for Reinforcement Learningcited by 8
  38. 2025Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Bindingcited by 8

50 most cited of 172 All 172 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making
  2. 2026MEDVISTAGYM: A Scalable Training Environment for Thinking with Medical Images via Tool-Integrated Reinforcement Learning
  3. 2026MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement
  4. 2026MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning
  5. 2025MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precision
  6. 2025Toward Effective Reinforcement Learning Fine-Tuning for Medical VQA in Vision-Language Models
  7. 2026Is There Knowledge Left to Extract? Evidence of Fragility in Medically Fine-Tuned Vision-Language Models
  8. 2025Reasoning Visual Language Model for Chest X-Ray Analysis