mlsanityData to 14 Oct 2026

Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation

arXiv 2603.16876 ↗First posted 17 Feb 2026cs.CV cs.AI cs.LGcited by 1

On the map: LLM agents and tool use → Medical and scientific domain agents

Abstract (arXiv)

We propose MARL-Rad, a multi-modal multi-agent reinforcement learning framework for radiology report generation that trains the entire agentic system on policy within its deployed radiology workflow. MARL-Rad addresses the limitation of post-hoc agentization, where fixed LLMs are organized into hand-designed agentic workflows without being optimized for their assigned roles. Our framework decomposes chest X-ray interpretation into region-specific agents and a global integrating agent, and jointly optimizes them using clinically verifiable rewards. Experiments on the MIMIC-CXR and IU X-ray datasets show that MARL-Rad consistently improves clinical efficacy metrics such as RadGraph, CheXbert, and GREEN scores, achieving state-of-the-art clinical efficacy performance. Further analyses show that MARL-Rad improves laterality consistency and produces more accurate and detailed reports. A blinded clinician evaluation further suggests that MARL-Rad produces reports clinically comparable to ground-truth reports.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use. Builds on 99 of its 138 references that are in the map. First posted on arXiv 17 Feb 2026.

Builds on

99 of 138 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflows24 Sep
  2. 2025Medical AI Consensus: A Multi-Agent Framework for Radiology Report Generation and Evaluation22 Sep
  3. 2025A Multimodal Multi-Agent Framework for Radiology Report Generation14 May

Other references · 96

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,796
  6. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,810
  7. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  9. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,808
  10. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  11. 2025Understanding R1-Zero-Like Training: A Critical Perspectivecited by 1,345
  12. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
38 more
  1. 2025Group Sequence Policy Optimizationcited by 835
  2. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
  3. 2023PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallelcited by 660
  4. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  5. 2020Generating Radiology Reports via Memory-driven Transformercited by 368
  6. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  7. 2020CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERTcited by 337
  8. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 336
  9. 2021RadGraph: Extracting Clinical Entities and Relations from Radiology Reportscited by 319
  10. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 311
  11. 2025Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMscited by 289
  12. 2023BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Taskscited by 201
  13. 2022Cross-modal Memory Networks for Radiology Report Generationcited by 185
  14. 2025ToRL: Scaling Tool-Integrated RLcited by 169
  15. 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Makingcited by 163
  16. 2021Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generationcited by 162
  17. 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learningcited by 161
  18. 2025Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domainscited by 156
  19. 2024MAIRA-2: Grounded Radiology Report Generationcited by 145
  20. 2025Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Modelscited by 144
  21. 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 140
  22. 2019Clinically Accurate Chest X-Ray Report Generationcited by 139
  23. 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automationcited by 131
  24. 2024GREEN: Generative Radiology Report Evaluation and Error Notationcited by 128
  25. 2023R2GenGPT: Radiology Report Generation with Frozen LLMscited by 114
  26. 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learningcited by 110
  27. 2025Agentic Large Language Models, a surveycited by 108
  28. 2023METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokenscited by 101
  29. 2025MAPoRL: Multi-Agent Post-Co-Training for Collaborative Large Language Models with Reinforcement Learningcited by 86
  30. 2023CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-trainingcited by 82
  31. 2022Competence-based Multimodal Curriculum Learning for Medical Report Generationcited by 76
  32. 2024MALT: Improving Reasoning with Multi-Agent LLM Trainingcited by 76
  33. 2023MAIRA-1: A specialised large multimodal model for radiology report generationcited by 74
  34. 2025Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learningcited by 72
  35. 2025In-the-Flow Agentic System Optimization for Effective Planning and Tool Usecited by 72
  36. 2023KiUT: Knowledge-injected U-Transformer for Radiology Report Generationcited by 62
  37. 2025Agent RL Scaling Law: Agent RL with Spontaneous Code Execution for Mathematical Problem Solvingcited by 62
  38. 2023XrayGPT: Chest Radiographs Summarization using Medical Vision-Language Modelscited by 61

50 most cited of 96 All 96 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026CogRad: A Cognitively-Inspired Multi-Agent Framework for Radiology Report Generationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Rethinking the Efficiency and Effectiveness of Reinforcement Learning for Radiology Report Generation
  2. 2026MARCH: Multi-Agent Radiology Clinical Hierarchy for CT Report Generation
  3. 2025Reason Like a Radiologist: Chain-of-Thought and Reinforcement Learning for Verifiable Report Generation
  4. 2025RadHiera: Semantic Hierarchical Reinforcement Learning for Medical Report Generation
  5. 2024How Well Can Modern LLMs Act as Agent Cores in Radiology Environments?
  6. 2026CXRMate-2: Structured Multimodal Temporal Embeddings and Tractable Reinforcement Learning for Clinically Acceptable Chest X-ray Radiology Report Generation
  7. 2026MAC-RRG: Iterative Multi-Agent Collaboration for X-ray Radiology Report Generation
  8. 2026Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning