Anmol Pandey, Aditya Jain, Liang Chen, Carsten Maple · 2026 · arXiv
DOI: 10.48550/arXiv.2610.27620 · open-access PDF
Agen LLM Otomatis bertindak melalui alat di bawah otorisasi per tindakan: seorang penjaga lokal memeriksa setiap panggilan alat secara terisolasi. Kami menunjukkan bahwa otorisasi lokal tidak membentuk otorisasi global. Kegagalan otorisasi komposisi (CAF) adalah eksekusi yang diautorisasi secara lokal, atau sepasang eksekusi yang diautorisasi secara lokal, yang melanggar tujuan, tujuan, asal usul, persetujuan, dan delegasi kebijakan global. Kami karakterisasi CAF di sepanjang dua sumbu, ekspresivitas (keselamatan satu jejak vs k-keselamatan relasional) dan observabilitas (tingkat profil monitor). Hasil pusat kami adalah hasil yang mustahil
Machine translation (Meta M2M100); the English original follows.
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 impossib
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange