arXiv — cs.AI preprintsInternational21 October 2026
Local Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents
This is an official announcement record
Firsthand records what arXiv — cs.AI preprints announced and links to the original. The wording below is theirs, not ours.
arXiv:2610.27620v1 Announce Type: cross 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 mo
Read the official announcement
Opens arxiv.org
More from arXiv — cs.AI preprints
- Navalia: Advancing Cowork Agents through Verifiable Task Synthesis and Long-Horizon Post-Training21 October 2026
- Large language model and reinforcement learning based autonomous construction and progress updates21 October 2026
- Pareto-Optimal RTL Code Generation via Multi-Objective Reinforcement Learning with Large Language Models21 October 2026
- MedPAO-Assist: Edge-Deployable, Modality-Aware Agentic AI for Radiology Report Structuring21 October 2026
- DataPraxis: Scaling Analytics Tasks via Verified Workspace Evolution21 October 2026
This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.