{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:28:14Z","timestamp":1773804494773,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"34","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>The application of vision-language models in medicine is critically hampered by the scarcity of high-quality, expert-annotated data. Supervised fine-tuning on existing datasets often leads to poor generalization on unseen modalities and tasks, while reinforcement learning, a promising alternative, is stymied by the lack of reliable reward signals in this data-scarce domain. To address this challenge, we propose a Generative Reward Learning framework that establishes a self-improving training cycle. The framework jointly develops a data generator and a reward model, enabling the automated and continuous creation of high-quality multimodal medical data that serves as an effective training source for post-training. Our experiments demonstrate that supervised fine-tuning using the generated data already surpasses models trained on large-scale human-curated datasets. More importantly, when the generated data is further leveraged for reinforcement learning via Group Relative Policy Optimization, the resulting model achieves state-of-the-art cross-modality and cross-task generalization, significantly outperforming specialized reinforcement-learning-based methods. Notably, a compact model trained under this framework attains performance competitive with foundation models containing more than an order of magnitude more parameters. These results suggest a new paradigm for data-efficient learning in high-stakes medical domains, shifting the bottleneck from data scarcity to data generation and unlocking the potential of reinforcement learning for building robust and generalizable medical AI systems.<\/jats:p>","DOI":"10.1609\/aaai.v40i34.40125","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:26:46Z","timestamp":1773800806000},"page":"28901-28909","source":"Crossref","is-referenced-by-count":0,"title":["MedGR2: Breaking the Data Barrier for Medical Reasoning via Generative Reward Learning"],"prefix":"10.1609","volume":"40","author":[{"given":"Weihai","family":"Zhi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiayan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2026,3,14]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40125\/44086","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40125\/44086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:26:46Z","timestamp":1773800806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40125"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"34","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i34.40125","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,14]]}}}