Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910200013783040 |
|---|---|
| author | Baba, Kaito Kishikawa, Risa Kodera, Satoshi |
| author_facet | Baba, Kaito Kishikawa, Risa Kodera, Satoshi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_16876 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation Baba, Kaito Kishikawa, Risa Kodera, Satoshi Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 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. |
| title | Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2603.16876 |