{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:33:48Z","timestamp":1773804828300,"version":"3.50.1"},"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>Self-training large language models (LLMs) with generated reasoning paths has emerged as a promising approach to improve performance on complex reasoning tasks. However, most existing methods rely on correctness-based supervision, treating samples that reach the correct answer as high-quality despite potentially flawed intermediate steps, leading to noisy training signals. In this work, we propose K-STaR (Knowledge-aware Self-Taught Reasoner), a self-training framework that verifies reasoning paths through knowledge elicitation and integration as a proxy, without requiring any external reward models or dense step-by-step annotations. K-STaR models reasoning as a structured composition of knowledge units and automatically assigns process rewards to intermediate steps via consistency and frequency analysis, ensuring that only knowledge-grounded reasoning paths are retained. Experiments on mathematical and commonsense reasoning tasks show that K-STaR consistently discovers higher-quality reasoning paths and achieves superior self-training performance compared to prior methods. Our results highlight the importance of moving beyond correctness-centric supervision toward knowledge-grounded self-improvement.<\/jats:p>","DOI":"10.1609\/aaai.v40i37.40423","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:46:00Z","timestamp":1773801960000},"page":"31573-31581","source":"Crossref","is-referenced-by-count":0,"title":["K-STaR: Knowledge-Aware Self-Taught Reasoner"],"prefix":"10.1609","volume":"40","author":[{"given":"Guozheng","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyu","family":"Zhang","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\/40423\/44384","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/40423\/44384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T02:46:05Z","timestamp":1773801965000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/40423"}},"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.v40i37.40423","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]]}}}