Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows· 代理 AI 工作流中的组合政策违规
Agentic workflows now make consequential decisions in regulated settings, and the governance placed around them is almost entirely step-scoped: input-output classifiers, per turn rails, and span-level evaluators. The policies organizations actually hold, such as referral thresholds, authority limits, and review requirements, are properties of the whole execution rather than of any one step. This mismatch admits a failure mode we call a Compositional Policy Violation (CPV): every individual step passes its own check while the composed execution violates the governing policy. A predicate over a single step cannot evaluate a property that step does not determine, so no improvement in the accuracy of the step-scoped monitors detects this class. We define CPVs as the failure of step-level compl
研究代理 AI 工作流中由于步骤合规未能保障整体合规而导致的政策违规问题。
- 核心方法
- 作者定义了组合政策违规(CPVs)的概念，指出单步骤合规检查的局限，并探讨了如何设计全流程的监测机制来识别这类违规。
- 适合谁读
- 研究者
- 要解决的问题
- 传统的单步骤合规检查方法无法识别和防止跨多个步骤的执行过程中的整体政策违规（CPV）。
- 关键实验
- 未提供
- 主要贡献
- 提出了组合政策违规(CPVs)这一新问题类型，并分析了其产生原因及现有治理方法的不足。
- 意义与局限
- 强调了在监管环境中全面考虑AI工作流合规性的重要性，但未提供具体解决方案或实验验证。