arXiv:2610. 39124v1 Announce Type: cross Abstract: Dangerous-capability evaluations often test an AI agent from prepared states at ordered milestones.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2609.06036v1 Announce Type: new Abstract: Proposal-based controllers---learned policies, language-model planners, and other black-box \emph{generators}---are increasingly deployed behind runtim...
arXiv:2605.29139v2 Announce Type: replace-cross Abstract: Question-answering services built on retrieval-augmented generation (RAG), in which a language model answers from retrieved documents, are in...
arXiv:2610.09541v1 Announce Type: cross Abstract: Signals that predict whether a chain-of-thought (CoT) trace is correct are compared by AUC, but deploying one requires a threshold with a guarantee....
arXiv:2610.33112v1 Announce Type: new Abstract: Use-based AI regulation assigns obligations by deployment risk but lacks an evidentiary object to carry them. A benchmark score is a property of a mode...
arXiv:2610.18948v1 Announce Type: cross Abstract: Finite safety assessments cannot exclude an adversary that preserves unattacked behavior until certification and activates afterward. We characterize...
The paper investigates how verifier components used in post‑training and test‑time loops can collapse when they are refreshed based on aggregate success scores. It shows that as a policy improves on one conjunctive target, the verifier’s on‑policy AUC can shift to favor a worse component, leading to a preference for a full‑outcome predictor over the intended component oracle. The authors provide theoretical thresholds, empirical demonstrations on text control and ECG data, and propose a repair that audits the component on its own failures to prevent damage.