{"slug": "assurance-conditioned-continuous-authorization-for-autonomous-ai-agents", "title": "Assurance-Conditioned Continuous Authorization for Autonomous AI Agents", "summary": "A new arXiv paper (2611.05632v1) presents Assurance-Conditioned Continuous Authorization (ACCA), a harness-independent approach for maintaining operational authority over autonomous AI agents based on currently justified assurance. ACCA separates evidence validity from contextual applicability, derives assurance claims from eligible evidence, and resolves a multidimensional effective-authority envelope within a principal-declared ceiling and applicable policy, using a typed dependency graph for selective re-evaluation and authority epochs that change when effective authority changes. Controlled scenario tests run as a regression suite under a trading Domain Governance Profile exercised default-deny rules, evidence-conditioned contraction and recovery, policy divergence, selective non-response, and stale-action rejection at a local gateway before a simulated-broker boundary; the authors state the work establishes implementation-level evidence in one domain, not a cross-domain guarantee of harmful-behavior prevention.", "body_md": "arXiv:2611.05632v1 Announce Type: new \nAbstract: Autonomous software agents can act through tools, delegate work, and change their models or execution environments while earlier authorizations remain in flight. We present Assurance-Conditioned Continuous Authorization (ACCA), an approach designed to be harness-independent, for maintaining operational authority according to currently justified assurance. It distinguishes evidence validity from contextual applicability, derives assurance claims from eligible evidence, and resolves a multidimensional effective-authority envelope within a principal-declared ceiling and applicable policy. A typed dependency graph supports selective re-evaluation of authorization-relevant changes. An authority epoch changes when effective authority changes; a distinct optional authorization-basis version supports revalidation of action-specific authorization conditions. Protected effect-time enforcement can reject stale actions before a consequential resource change, subject to the available commit mechanism. A compositional Domain Governance Profile expresses domain-specific semantics without granting authority. Controlled scenario tests implemented as a regression suite using a trading profile exercise default-deny rules, evidence-conditioned contraction and recovery, policy divergence, selective non-response, and stale-action rejection at a local gateway before the simulated-broker boundary. The study establishes implementation-level evidence in one domain, not a cross-domain guarantee of harmful-behavior prevention.", "url": "https://wpnews.pro/news/assurance-conditioned-continuous-authorization-for-autonomous-ai-agents", "canonical_source": "https://arxiv.org/abs/2611.05632", "published_at": "2026-11-05 05:00:00+00:00", "updated_at": "2026-11-05 05:22:04.343895+00:00", "lang": "en", "topics": ["ai-agents", "ai-safety", "ai-policy"], "entities": ["Assurance-Conditioned Continuous Authorization", "ACCA", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/assurance-conditioned-continuous-authorization-for-autonomous-ai-agents", "markdown": "https://wpnews.pro/news/assurance-conditioned-continuous-authorization-for-autonomous-ai-agents.md", "text": "https://wpnews.pro/news/assurance-conditioned-continuous-authorization-for-autonomous-ai-agents.txt", "jsonld": "https://wpnews.pro/news/assurance-conditioned-continuous-authorization-for-autonomous-ai-agents.jsonld"}}