Truthful Reverse Auctions for Adaptive Selection via Contextual Multi-Armed Bandits
Abstract
We study the problem of selecting large language models (LLMs) for user queries in settings where multiple LLM providers submit the cost of solving a query. From the users' perspective, choosing an optimal model is a sequential, query-dependent decision problem: high-capacity models offer more reliable outputs but are costlier, while lightweight models are faster and cheaper. We formalize this interaction as a reverse auction design problem with contextual online learning, where the user adaptively discovers which model performs best while eliciting costs from competing LLM providers. Existing multi-armed bandit (MAB) mechanisms focus on forward auctions and social welfare, leaving open the challenges of reverse auctions, provider-optimal outcomes, and contextual adaptation. We address these gaps by designing a resampling-based procedure that generalizes truthful forward MAB mechanisms to reverse auctions and prove that any monotone allocation rule with this procedure is truthful. Using this, we propose a contextual MAB algorithm that learns query-dependent model quality with sublinear regret. Our framework unifies mechanism design and adaptive learning, enabling efficient, truthful, and query-aware LLM selection.
Cite
@article{arxiv.2602.14476,
title = {Truthful Reverse Auctions for Adaptive Selection via Contextual Multi-Armed Bandits},
author = {Pronoy Patra and Sankarshan Damle and Manisha Padala and Sujit Gujar},
journal= {arXiv preprint arXiv:2602.14476},
year = {2026}
}
Comments
20 pages, 6 figures