CAVA：用于智能代理人工智能系统运行时治理的规范动作验证与认证
CAVA: Canonical Action Verification and Attestation for Runtime Governance of Agentic AI Systems
查看机构详情
- Ond Holdings Inc（Ond控股公司）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
研究智能代理人工智能系统异构运行时带来的治理问题。提出CAVA，将异构代理活动转换为规范动作对象。通过基准参考实现研究，为部署者端人工智能治理提供动作级规范化和语义模式的系统表述。
中文摘要 AI 辅助
智能代理人工智能系统越来越多地通过异构运行时来运行，如本地编码钩子、SDK工具等。单个操作行为可能由许多不兼容的运行时记录表示，这使得基本治理问题难以回答。本文提出了规范动作验证与认证（CAVA），它是一个运行时语义层，将异构代理活动转换为规范的运行时动作对象。CAVA位于带证明的代理动作（PCAA）之下，本文形式化了规范动作标识等内容。通过一个包含96个种子、384个变体的基准进行了参考实现研究，贡献是为部署者端人工智能治理提供了动作级规范化和策略可寻址语义模式的系统表述。
英文摘要
Agentic AI systems increasingly act through heterogeneous runtimes: local coding hooks, SDK tools, browser automation, managed-agent traces, API gateways, and workflow engines. A single operational act such as publishing code, changing identity state, moving money, or exporting data may therefore be represented by many incompatible runtime records. This makes a basic governance question difficult to answer: what action was actually approved, what evidence binds the approval to execution, and can an independent verifier reproduce the same action identity later? This paper presents Canonical Action Verification and Attestation (CAVA), a runtime-semantics layer for converting heterogeneous agent activity into canonical runtime action objects. CAVA is positioned below Proof-Carrying Agent Actions (PCAA): PCAA defines the deployer-owned route-review-prove governance process, while CAVA defines the stable action object that process governs. The paper formalizes canonical action identity, semantic pattern detection, approval binding, receipt integrity, runtime-portable projection, and optional attestation substrates. We study a reference implementation through a 96-seed, 384-variant benchmark covering semantic equivalence, semantic separation, wrapper bypass, false-positive control, approval binding, receipt reproducibility, attestation tamper detection, runtime portability, semantic pattern detection, policy degradation, and Azure deployment drills. The contribution is a systems formulation of action-level canonicalization and policy-addressable semantic patterns as a necessary substrate for deployer-side AI governance.
