arXiv Machine Learning By Lauri Lov\'en, Nam Do, Hassan Mehmood, Dinesh Kumar Sah, Sasu Tarkoma

The Behavioral Credibility Trilemma: When Calibrated Autonomy Becomes Impossible

Read the original on arXiv Machine Learning →

arXiv:2605. 25739v2 Announce Type: replace Abstract: We prove that no reinforcement learning policy with confidence-gated autonomy can simultaneously achieve maximum helpfulness, optimal calibration, and full autonomy under rational oversight, whenever some tasks exceed the agent's reliable competence: the Behavioral Credibility Trilemma.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers
Jul 14

Resist and Update: Counterfactual Report Coordinates for Incentive-Compatible LLMs

Aligned language models routinely misreport under non-evidential incentive pressure: they agree with a confident user or overstate certainty even when their internal belief is unchanged. We cast this as a failure of internal incentive-compatibility (IC) and present a method for learning and certifying counterfactual report mediators that hold a model's reports to a causal contract: invariant to forbidden influences (pressure, prestige, restyling) and responsive to licensed ones (genuine evidence).