{"slug": "from-agent-failure-paths-to-quantified-residual-risk-a-compositional-framework", "title": "From Agent Failure Paths to Quantified Residual Risk: A Compositional Framework for Resilient Agentic AI", "summary": "A new compositional framework called CPSAINT, paired with the FRIESA-K residual-risk functional, provides a quantified risk estimate for agentic AI by decomposing failure paths across seven layers and grounding resistance in a controlled absorbing Markov model. The framework, detailed in arXiv:2607.18243v1, demonstrates cross-domain applicability on a warehouse robot and a financial-services agent, offering a mechanism-to-magnitude pipeline for resilient embodied AI.", "body_md": "arXiv:2607.18243v1 Announce Type: new\nAbstract: 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. 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. 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. 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. 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.", "url": "https://wpnews.pro/news/from-agent-failure-paths-to-quantified-residual-risk-a-compositional-framework", "canonical_source": "https://arxiv.org/abs/2607.18243", "published_at": "2026-07-22 04:00:00+00:00", "updated_at": "2026-07-22 04:11:54.345162+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-research", "ai-agents"], "entities": ["CPSAINT", "FRIESA-K", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/from-agent-failure-paths-to-quantified-residual-risk-a-compositional-framework", "markdown": "https://wpnews.pro/news/from-agent-failure-paths-to-quantified-residual-risk-a-compositional-framework.md", "text": "https://wpnews.pro/news/from-agent-failure-paths-to-quantified-residual-risk-a-compositional-framework.txt", "jsonld": "https://wpnews.pro/news/from-agent-failure-paths-to-quantified-residual-risk-a-compositional-framework.jsonld"}}