mlsanityData to 7 Oct 2026

GMAI-VL-R1: Harnessing Reinforcement Learning for Multimodal Medical Reasoning

arXiv 2504.01886 ↗First posted 2 Apr 2025cs.CVcited by 39

On the map: LLM reasoning → Clinical and biomedical applications

Abstract (arXiv)

Recent advances in general medical AI have made significant strides, but existing models often lack the reasoning capabilities needed for complex medical decision-making. This paper presents GMAI-VL-R1, a multimodal medical reasoning model enhanced by reinforcement learning (RL) to improve its reasoning abilities. Through iterative training, GMAI-VL-R1 optimizes decision-making, significantly boosting diagnostic accuracy and clinical support. We also develop a reasoning data synthesis method, generating step-by-step reasoning data via rejection sampling, which further enhances the model's generalization. Experimental results show that after RL training, GMAI-VL-R1 excels in tasks such as medical image diagnosis and visual question answering. While the model demonstrates basic memorization with supervised fine-tuning, RL is crucial for true generalization. Our work establishes new evaluation benchmarks and paves the way for future advancements in medical reasoning models. Code, data, and model will be released at hrefhttps://github.com/uni-medical/GMAI-VL-R1this link.

Key facts. Cited by 39 papers in the map (data through 7 Oct 2026). Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning. First posted on arXiv 2 Apr 2025.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 25; 2026: 14.

39 papers.

Sort:

By area:

  1. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 74
  2. 2026A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agentscited by 47
  3. 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoningcited by 37
  4. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 34
  5. 2025X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domainscited by 30
  6. 2025MedVLThinker: Simple Baselines for Multimodal Medical Reasoningcited by 26
  7. 2025Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Searchcited by 16
  8. 2025Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learningcited by 14
  9. 2026PyVision-RL: Forging Open Agentic Vision Models via RLcited by 14
  10. 2025UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysiscited by 12
  11. 2026MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolutioncited by 12
  12. 2025Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applicationscited by 10
27 more
  1. 2025OralGPT-Omni: A Versatile Dental Multimodal Large Language Modelcited by 10
  2. 2025SciReasoner: Laying the Scientific Reasoning Ground Across Disciplinescited by 9
  3. 2025MedQ-Bench: Evaluating and Exploring Medical Image Quality Assessment Abilities in MLLMscited by 9
  4. 2025Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoningcited by 8
  5. 2025Elicit and Enhance: Advancing Multimodal Reasoning in Medical Scenarioscited by 6
  6. 2025ShizhenGPT: Towards Multimodal LLMs for Traditional Chinese Medicinecited by 6
  7. 2025Bridging the Gap in Ophthalmic AI: MM-Retinal-Reason Dataset and OphthaReason Model toward Dynamic Multimodal Reasoningcited by 6
  8. 20253DReasonKnee: Advancing Grounded Reasoning in Medical Vision Language Modelscited by 5
  9. 2025DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistrycited by 5
  10. 2025Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesiscited by 3
  11. 2026MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcementcited by 3
  12. 2026Omni-MMSI: Toward Identity-attributed Social Interaction Understandingcited by 3
  13. 2025InfiMed: Low-Resource Medical MLLMs with Advancing Understanding and Reasoningcited by 2
  14. 2025Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMscited by 2
  15. 2026ClinFusion: A Vision-Centric Multimodal LLM System for Holistic Medical Understandingcited by 2
  16. 2025Proactive Reasoning-with-Retrieval Framework for Medical Multimodal Large Language Modelscited by 1
  17. 2026Incentivizing Cardiologist-Like Reasoning in MLLMs for Interpretable Echocardiographic Diagnosiscited by 1
  18. 2026Topo-R1: Detecting Topological Anomalies via Vision-Language Modelscited by 1
  19. 2026MedProbeBench: Systematic Benchmarking at Deep Evidence Integration for Expert-level Medical Guidelinecited by 1
  20. 2026Breaking Failure Cascades: Step-Aware Reinforcement Learning for Medical Multimodal Reasoningcited by 1
  21. 2026Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoningcited by 1
  22. 2025SpinalSAM-R1: A Vision-Language Multimodal Interactive System for Spine CT Segmentationcited by 0
  23. 2025Colon-X: Advancing Intelligent Colonoscopy toward Clinical Reasoningcited by 0
  24. 2025Benchmark Success, Clinical Failure: When Reinforcement Learning Optimizes for Benchmarks, Not Patientscited by 0
  25. 2026MedQ-Deg: A Multidimensional Benchmark for Evaluating MLLMs Across Medical Image Quality Degradationscited by 0
  26. 2026CARE: Causally-Aligned Reasoning Exploration for Medical Large Language Modelscited by 0
  27. 2026CineMR: Tool-Integrated Vision-Language Reasoning for Quantitative Cardiac MRI Assessmentcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models
  2. 2025RARL: Improving Medical VLM Reasoning and Generalization with Reinforcement Learning and LoRA under Data and Hardware Constraints
  3. 2025Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning
  4. 2025MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning
  5. 2025Adaptive Reinforcement for Open-ended Medical Reasoning via Semantic-Guided Reward Collapse Mitigation
  6. 2025Improving Medical Reasoning with Curriculum-Aware Reinforcement Learning
  7. 2025Med-RLVR: Emerging Medical Reasoning from a 3B base model via reinforcement Learning
  8. 2025CAPO: Reinforcing Consistent Reasoning in Medical Decision-Making