Metraipolis › archive › dc_55ea769ba42b
The Confidence Game: Strategic Miscalibration in Human-AI Delegation — arXiv:2610.09371
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.09371
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T11:10:56.671Z
- SHA-256 of the archived text
f67a570f003b99bdb51c507967a40d931557593503319d8b48d0f72f309aca7d- Stable URL of this page
https://metraipolis.com/documento/dc_55ea769ba42b
How to cite
The Confidence Game: Strategic Miscalibration in Human-AI Delegation — arXiv:2610.09371 — arXiv (en), https://arxiv.org/abs/2610.09371 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_55ea769ba42b (Metraipolis archive dc_55ea769ba42b, sha256 f67a570f003b99bdb51c507967a40d931557593503319d8b48d0f72f309aca7d)
BibTeX
@misc{dc55ea769ba42b,
title = {The Confidence Game: Strategic Miscalibration in Human-AI Delegation — arXiv:2610.09371},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.09371},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_55ea769ba42b; sha256 f67a570f003b99bdb51c507967a40d931557593503319d8b48d0f72f309aca7d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09371. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Calibrated uncertainty quantification is essential to ensuring AI agents are trustworthy and reliable. However, when agents seek to maximize user engagement or revenue, confidence reports may be strategically distorted, detracting from their informativeness. We formalize this problem in the Confidence Game: a repeated signaling game with imperfect monitoring in which an agent of unknown honesty and ability reports its confidence, and a user decides whether to delegate the task or complete it herself. The agent manages the tradeoff between manipulating signals and maintaining its reputation. We characterize the Markov Perfect Bayesian Equilibria of the two-period game and show that honest reporting is not an equilibrium, inflation is the unique best response once the agent is sufficiently myopic, and under-reporting requires that the user believe honesty to be a minority. We then place an LLM in the agent role, supplying it with its true probability of success so that any gap between what it knows and what it reports is attributable to incentives rather than to miscalibration. The model claims high confidence on 56% of tasks it has been told it will probably fail. This persists on real tasks, where it must estimate its own accuracy and causes miscalibration to increase while the agent's signal becomes less informative. Furthermore, we find that the LLM agent's decisions are coherent, but it systematically underestimates both how likely the user is to delegate and how secure its reputation is, resulting in less extreme behavior. Pricing the agent's reporting rule, we find that it destroys 68% of the gains from delegation, of which 71% is information the report no longer carries and no amount of user sophistication recovers. Overall, we establish confidence reporting under delegation as a strategic problem and provide a tractable basis for modeling, analyzing, and testing agent behavior. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Science and Game Theory (cs.GT) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY); Human-Computer Interaction (cs.HC). Pagina del lavoro: https://arxiv.org/abs/2610.09371 — 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 2026-10-08T10:14:06.081Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).