Sign inGet started
Paper · arXiv

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

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 bla...

AuthorsAnmol Pandey, Aditya Jain, Liang Chen et al.
Primary categorycs.CR
Published20 October 2026
Last updated at source20 October 2026
cs.CRcs.AIcs.LO
Embed this entry
<iframe src="https://silytics.si/embed/item/c824320b-7b2e-498f-8002-59a2da15a929" width="420" height="190" style="border:0" loading="lazy" title="Silytics entry"></iframe>

Free, no tracking. More about feeds and embeds.

Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 21 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.