{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:55:30Z","timestamp":1781193330854,"version":"3.54.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"37","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Medical language models face critical barriers to real-world clinical reasoning applications. \nHowever, mainstream efforts, which fall short in task coverage, lack fine-grained supervision for intermediate reasoning steps, and rely on proprietary systems, are still far from a versatile, credible and efficient language model for clinical reasoning usage.\nTo this end, we propose MedS3, a self-evolving framework that imparts robust reasoning capabilities to small, deployable models. \nStarting with 8,000 curated instances sampled via a curriculum strategy across five medical domains and 16 datasets, we use a small base policy model to conduct Monte Carlo Tree Search (MCTS) for constructing rule-verifiable reasoning trajectories. \nSelf-explored reasoning trajectories ranked by node values are used to bootstrap the policy model via reinforcement fine-tuning and preference learning. \nMoreover, we introduce a soft dual process reward model that incorporates value dynamics: steps that degrade node value are penalized, enabling fine-grained identification of reasoning errors even when the final answer is correct.\nExperiments on eleven benchmarks show that MedS3 outperforms the previous state-of-the-art medical model by +6.45 accuracy points and surpasses 32B-scale general-purpose reasoning models by +8.57 points.\nAdditional empirical analysis further demonstrates that MedS3 achieves robust and faithful reasoning behavior.<\/jats:p>","DOI":"10.1609\/aaai.v40i37.40395","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:43:25Z","timestamp":1773801805000},"page":"31319-31327","source":"Crossref","is-referenced-by-count":1,"title":["MedS\u00b3: Towards Medical Slow Thinking with Self-Evolved Soft Dual-sided Process Supervision"],"prefix":"10.1609","volume":"40","author":[{"given":"Shuyang","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusheng","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanfeng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"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\/40395\/44356","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40395\/44356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:43:26Z","timestamp":1773801806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40395"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"37","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i37.40395","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]]}}}