{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T03:07:35Z","timestamp":1773803255605,"version":"3.50.1"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"29","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"<jats:p>Large language models (LLMs) exhibit diverse response behaviors, costs, and strengths, making it challenging to select the most suitable LLM for a given user query. We study the problem of adaptive multi-LLM selection in an online setting, where the learner interacts with users through multi-step query refinement and must choose LLMs sequentially without access to offline datasets or model internals. A key challenge arises from unstructured context evolution: the prompt dynamically changes in response to previous model outputs via a black-box process, which cannot be simulated, modeled, or learned. To address this, we propose the first contextual bandit framework for sequential LLM selection under unstructured prompt dynamics. We formalize a notion of myopic regret and develop a LinUCB-based algorithm that provably achieves sublinear regret without relying on future context prediction. We further introduce budget-aware and positionally-aware (favoring early-stage satisfaction) extensions to accommodate variable query costs and user preferences for early high-quality responses. Our algorithms are theoretically grounded and require no offline fine-tuning or dataset-specific training. Experiments on diverse benchmarks demonstrate that our methods outperform existing LLM routing strategies in both accuracy and cost-efficiency, validating the power of contextual bandits for real-time, adaptive LLM selection.<\/jats:p>","DOI":"10.1609\/aaai.v40i29.39672","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:46:19Z","timestamp":1773798379000},"page":"24855-24863","source":"Crossref","is-referenced-by-count":0,"title":["Online Multi-LLM Selection via Contextual Bandits Under Unstructured Context Evolution"],"prefix":"10.1609","volume":"40","author":[{"given":"Manhin","family":"Poon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangxiang","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xutong","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fang","family":"Kong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John C.S.","family":"Lui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinhang","family":"Zuo","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\/39672\/43633","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/39672\/43633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:46:20Z","timestamp":1773798380000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/39672"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,14]]},"references-count":0,"journal-issue":{"issue":"29","published-online":{"date-parts":[[2026,3,17]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v40i29.39672","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]]}}}