Metraipolis › archive › dc_2b7d66b2aea2
Anytime Contracts for AI Services — arXiv:2610.22781
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22781
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:44:32.201Z
- SHA-256 of the archived text
476284ae0beb878ff9336bb2095ed2ff6cab82a89dceb3f938bc71b306e17503- Stable URL of this page
https://metraipolis.com/documento/dc_2b7d66b2aea2
How to cite
Anytime Contracts for AI Services — arXiv:2610.22781 — arXiv (en), https://arxiv.org/abs/2610.22781 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b7d66b2aea2 (Metraipolis archive dc_2b7d66b2aea2, sha256 476284ae0beb878ff9336bb2095ed2ff6cab82a89dceb3f938bc71b306e17503)
BibTeX
@misc{dc2b7d66b2aea2,
title = {Anytime Contracts for AI Services — arXiv:2610.22781},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22781},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b7d66b2aea2; sha256 476284ae0beb878ff9336bb2095ed2ff6cab82a89dceb3f938bc71b306e17503},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22781. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
AI services are prone to moral hazard, as model providers can silently route requests to cheaper, lower-quality models, and the inherent stochasticity of model outputs makes this degradation hard to detect. Contract theory addresses moral hazard by designing payment rules that reward high-quality outputs and prevent strategic overcharging. However, existing frameworks assume interactions of fixed duration, whereas AI services are typically consumed through subscriptions and pay-as-you-go APIs that users can terminate at any time based on observed performance. We show that this flexibility can break standard contracts, opening them up to abuse by either the providers or users. To address this, we extend contract theory to account for unknown exit rules. We formalize the problem as a Principal-Agent game, and show that budget-optimal contracts in this setting are proportional to anytime-valid hypothesis tests based on likelihood-ratio e-values. We give an efficient algorithm for computing anytime contracts and show how betting e-processes can be used to approximate them when the models are unknown. Finally, we evaluate our findings on synthetic data and data from deployed LLMs. Tema degli esploratori: economia dei servizi IA (elenco arXiv cs.GT, nuovi lavori del giorno). Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.22781 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:40:39.821Z dalla pagina https://arxiv.org/list/cs.GT/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).