From Agent Failure Paths to Quantified Residual Risk: A Compositional Framework for Resilient Agentic AI

从智能体故障路径到量化残余风险：一种用于弹性智能体 AI 的组合框架

Abstract: Agentic AI is crossing trust boundaries faster than current risk models can represent. Existing approaches provide one of two partial views. They either describe failure mechanisms without producing a transferable residual-risk estimate, or they produce a risk estimate while treating the internal failure path as a black box.

摘要： 智能体 AI（Agentic AI）跨越信任边界的速度远超当前风险模型的表征能力。现有的方法通常只能提供两种片面视角之一：要么描述故障机制却无法产生可迁移的残余风险评估，要么在产生风险评估时将内部故障路径视为“黑盒”。

We couple those two views by proposing CPSAINT, a seven-layer integrity decomposition over Physical state, Sensors, Data, Compute, Actuators, Environment, and Time, paired with FRIESA-K, a residual-risk functional that maps each failure path to a quantified risk instance.

我们通过提出 CPSAINT 将这两种视角结合起来。CPSAINT 是一种七层完整性分解框架，涵盖物理状态（Physical state）、传感器（Sensors）、数据（Data）、计算（Compute）、执行器（Actuators）、环境（Environment）和时间（Time）；并配以 FRIESA-K，这是一种残余风险函数，能够将每条故障路径映射为量化的风险实例。

FRIESA-K grounds the resistance term K in a controlled absorbing Markov model so that control effectiveness is derived from state dynamics rather than assigned as an informal score. The result is a concise mechanism-to-magnitude pipeline for resilient agentic and embodied AI.

FRIESA-K 将阻力项 K 建立在受控吸收马尔可夫模型（controlled absorbing Markov model）之上，从而使控制有效性源于状态动力学，而非作为非正式评分进行分配。其结果是为弹性智能体和具身智能（Embodied AI）提供了一条简洁的“机制到量级”流水线。

We report governance observability through a separate additive penalty instead of inserting governance as a new variable in the resistance functional. We formalize structural composability linking valid failure paths to well-defined risk instances and show the framework on two contrasting scenarios: a hard real-time warehouse robot and a governance-instrumented financial-services agent.

我们通过独立的加性惩罚项来报告治理可观测性，而不是将治理作为新变量插入到阻力函数中。我们形式化了结构组合性，将有效的故障路径与定义明确的风险实例联系起来，并在两个对比鲜明的场景中展示了该框架：硬实时仓库机器人和受治理约束的金融服务智能体。

Across both cases, the same layer grammar, variable semantics, and dynamic-resistance construction remain intact. Thus, we obtain a compact kernel that supports cross-domain reasoning, explicit assumptions, and quantitatively grounded formalism of composable trust.

在这两种情况下，相同的层级语法、变量语义和动态阻力构建方式均保持不变。因此，我们获得了一个紧凑的内核，支持跨领域推理、显式假设以及基于量化基础的可组合信任形式化。