面向自主 AI 智能体的保障条件化持续授权机制（ACCA）
Assurance-Conditioned Continuous Authorization for Autonomous AI Agents
AI 导读
研究者提出保障条件化持续授权（ACCA），一种独立于执行框架的方法，用于根据当前有效的保障状态持续维持自主智能体的操作权限。该方法区分证据有效性与情境适用性，在主体声明的权限上限和适用策略内求解多维有效权限包络，并借助类型化依赖图支持选择性重新评估。基于交易配置的受控场景回归测试验证了默认拒绝、证据条件化收缩与恢复、过期动作拒绝等规则，但仅在一个领域提供实现级证据，不构成跨领域危害行为防范保证。
正文 · 原文
Abstract: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.
| Comments: | 81 pages, 3 figures |
| Subjects: | Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2611.05632 [cs.AI] |
| (or arXiv:2611.05632v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05632 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Mehdi Shajari [view email]
[v1]
Tue, 3 Nov 2026 21:19:46 UTC (103 KB)
来源：arXiv cs.AI · arxiv.org