Newest papers

Local Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents

Anmol Pandey, Aditya Jain, Liang Chen, Carsten Maple · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27620 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Автономное подписание является единственным агентом сигнализации, действующим через одни и те же инструменты под разрешением на действие: местный охранник отображает каждый призыв инструмента в изоляции. Мы показываем, что местное разрешение не состоит в глобальном авторизации. Композиционный сбой в авторизации (CAF) является локально уполномоченным выполнением, или парой локально уполномоченных исполнений, которые нарушают глобальную политику охватывающей цель, цель, происхождение, согласие и делегирование. Мы характеризуем CAF по двум осям, экспрессивность (одиночный следовой контроль над безопасностью против относительной k-безопасности) и наблюдаемость (лагерь профилей мониторинга). Наш центральный результат является невозможностью:

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

Abstract

Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authorization does not compose into global authorization. A compositional authorization failure (CAF) is a locally authorized execution, or a pair of locally authorized executions, that violates a global policy spanning intent, purpose, provenance, consent, and delegation. We characterize CAFs along two axes, expressiveness (single-trace safety versus relational k-safety) and observability (a ladder of monitor profiles). Our central result is an impossibility: relational purpose violations form a 2-safety hyperproperty with no per-trace locus of blame, so a per-action monitor that never raises a false alarm detects none of them, independent of the underlying model or decision procedure; they become visible only under cross-execution monitoring, which none of the six guardrails we survey implements. We make this constructive with AL-SYNTH, a SAT/SMT synthesizer (using no language model) that emits minimal CAF witnesses, each checked against an exhaustive oracle. The empirical signature is sharp: across nine LLM judges the per-action view approves the synthesized witness almost without exception, blocking it at a rate comparable to a benign control, yet the same models flag it when shown the two executions together. Per-action authorization is therefore structurally insufficient for relational policy conjuncts not reducible to single-trace safety: to bound them, a monitor must compare executions or accept false alarms.

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

Topics: Computer science, Guard (computer science), Computer security, Constructive, Authorization, Bridging (networking)

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=2610.27620, 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