构建故障层级与意识映射，提升生成式AI系统的可靠性认知。
From Failure Modes to Reliability Awareness in Generative and Agentic AI System
- 提出11层故障栈，系统化识别从硬件到智能推理的脆弱环节。
- 发现故障常跨层传播，引发连锁失效，威胁系统整体可靠性。
- 开发意识映射框架，助力组织量化风险认知，指导可信AI治理。
本章通过将技术分析与组织准备相衔接，梳理了从多层故障模式到生成式与代理型AI系统可靠性认知的路径。首先引入一个11层故障栈，作为识别从硬件、供电基础到自适应学习和代理推理等层面漏洞的结构化框架。在此基础上，本文表明故障很少孤立发生，而会跨层传播，产生具有系统性后果的级联效应。为补充这一诊断视角，我们提出了意识映射概念：一种以成熟度为导向的框架，用于量化个人与组织在AI栈各层中对可靠性风险的认知水平。意识不仅被视作诊断评分，更作为人工智能治理的战略输入，指导改进与韧性规划。通过将分层故障与意识水平关联，并进一步整合进以可靠性为中心的资产管理（DCAM），本章将意识映射定位为可信赖且可持续部署关键任务领域AI的测量工具与路线图。
原文摘要 · Abstract (English)
This chapter bridges technical analysis and organizational preparedness by tracing the path from layered failure modes to reliability awareness in generative and agentic AI systems. We first introduce an 11-layer failure stack, a structured framework for identifying vulnerabilities ranging from hardware and power foundations to adaptive learning and agentic reasoning. Building on this, the chapter demonstrates how failures rarely occur in isolation but propagate across layers, creating cascading effects with systemic consequences. To complement this diagnostic lens, we develop the concept of awareness mapping: a maturity-oriented framework that quantifies how well individuals and organizations recognize reliability risks across the AI stack. Awareness is treated not only as a diagnostic score but also as a strategic input for AI governance, guiding improvement and resilience planning. By linking layered failures to awareness levels and further integrating this into Dependability-Centred Asset Management (DCAM), the chapter positions awareness mapping as both a measurement tool and a roadmap for trustworthy and sustainable AI deployment across mission-critical domains.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。