组合策略违规：当步骤级合规在智能体AI工作流中失效
Compositional Policy Violations: When Step-Level Compliance Fails In Agentic AI Workflows
浏览论文内容
中文总结 AI 辅助
针对智能体工作流中步骤级合规与整体策略不一致导致的组合策略违规问题，提出四类分类法及基于溯源感知的运行时架构，通过完整轨迹评估策略以修复违规。
中文摘要 AI 辅助
智能体工作流如今在受监管的环境中做出具有重大影响的决策，而围绕它们设置的治理几乎完全是以步骤为范围的：输入输出分类器、每轮护栏以及跨度级评估器。组织实际持有的策略，如转介阈值、权限限制和审查要求，是整个执行过程的属性，而非任何单个步骤的属性。这种不匹配导致了一种我们称之为组合策略违规（CPV）的失败模式：每个单独的步骤都通过了自身的检查，而组合后的执行却违反了治理策略。对单个步骤的谓词无法评估该步骤未决定的属性，因此步骤级监控器准确性的任何提升都无法检测到此类问题。我们将CPV定义为步骤级合规无法组合的失败，并提出了一个包含四种类型的分类法：权限蔓延、阈值洗钱、累计总和违规和上下文崩溃。我们表明，每一类正确的修复方式由受保护数量发生变异的位置决定。随后，我们引入了一种具有溯源感知的运行时架构，该架构在完整的执行轨迹上评估策略，从原始溯源而非流程的派生表示中重新计算受保护数量。
英文摘要
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 compliance to compose, and present a taxonomy of four types: Authority Creep, Threshold Laundering, Cumulative Sum Violation, and Context Collapse. We show that the correct repair for each class is dictated by where the guarded quantity mutates. We then introduce a provenance-aware runtime architecture that evaluates policies over complete execution traces, recomputing guarded quantities from raw provenance rather than the pipeline's derived representation.
发表机构
- RunCtrl
机构由 AI 辅助整理，请以论文原文为准。
