Newest papers

Correlated Failures of AI Approval Monitors

Luca Zanolini · 2026 · arXiv

DOI: 10.48550/arXiv.2610.29178 · open-access PDF

Japanese

AIエージェントが、支払い、メッセージ、コードを変更するなどの結果的なアクションを取る前に、複数のモニターがそれをチェックします。彼らの判決は、合計スコアまたは承認を数えることによって組み合わされます。モニターの入力が何であれ共有されます。ベースモデルまたは毒入力を共有するモニターは、しかし、共に失敗する可能性があります。我々は分散型コンピューティングの故障傾向のシステムを貸します:共に失敗する可能性のあるモニターセットのリストです。 2つの事前登録されたプロトコルで支払い承認について12の小型オープンワイヤーモニターを測定しました。

Machine translation (Meta M2M100); the English original follows.

Abstract

Before an AI agent takes a consequential action, such as paying, messaging or changing code, several monitors check it. Their verdicts are combined by aggregating scores or by counting approvals, whatever inputs the monitors share. Monitors that share a base model or a poisoned input, however, may fail together. We borrow the fail-prone systems of distributed computing: lists of monitor sets that may fail together. A rule is safe if it executes no bad action and live if it blocks no good one. We measured twelve small open-weights monitors on payment approval under two pre-registered protocols.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29178, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange