← Back ◬ AI & Machine Learning Mar 19, 2026

Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation: Radiologist-Like Workflow with Clinically Verifiable Rewards

arXiv AI Archived Mar 19, 2026 ✓ Full text saved

arXiv:2603.16876v1 Announce Type: cross Abstract: We propose MARL-Rad, a novel multi-modal multi-agent reinforcement learning framework for radiology report generation that coordinates region-specific agents and a global integrating agent, optimized via clinically verifiable rewards. Unlike prior single-model reinforcement learning or post-hoc agentization of independently trained models, our method jointly trains multiple agents and optimizes the entire agent system through reinforcement learni

Full text archived locally

✦ AI Summary · Claude Sonnet

Computer Science > Computer Vision and Pattern Recognition [Submitted on 17 Feb 2026] Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation: Radiologist-Like Workflow with Clinically Verifiable Rewards Kaito Baba, Satoshi Kodera We propose MARL-Rad, a novel multi-modal multi-agent reinforcement learning framework for radiology report generation that coordinates region-specific agents and a global integrating agent, optimized via clinically verifiable rewards. Unlike prior single-model reinforcement learning or post-hoc agentization of independently trained models, our method jointly trains multiple agents and optimizes the entire agent system through reinforcement learning. Experiments on the MIMIC-CXR and IU X-ray datasets show that MARL-Rad consistently improves clinically efficacy (CE) metrics such as RadGraph, CheXbert, and GREEN scores, achieving state-of-the-art CE performance. Further analyses confirm that MARL-Rad enhances laterality consistency and produces more accurate, detail-informed reports. Comments: 17 pages, 3 figures Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) Cite as: arXiv:2603.16876 [cs.CV] (or arXiv:2603.16876v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2603.16876 Focus to learn more Submission history From: Kaito Baba [view email] [v1] Tue, 17 Feb 2026 12:48:32 UTC (3,340 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CV < prev | next > new | recent | 2026-03 Change to browse by: cs cs.AI cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

💬 Team Notes