发表机构
Zhengzhou University（郑州大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对不可逆资源耗竭下的故障恢复，提出最后机会策略识别（LCPI）框架，以区分或同化原则评估可达状态正确性，并设计风险预算兼容性规划（RBCP）算法，在硬失败约束下提升风险可行恢复。
AI 中文摘要
在不可逆资源耗竭下，智能体可以花费资源来区分潜在故障模型，或者改变系统状态，使剩余模型允许一个共同的可接受延续——此时进一步的诊断变得不再必要。这一区分或同化原则识别出一条现有识别、规划和诊断框架未明确指出的路径：先前的公式将故障模型到可接受策略的映射视为给定，而LCPI使其成为智能体自身行为的函数。我们通过最后机会策略识别（LCPI）形式化这一原则，其中正确性在智能体达到的状态而非初始状态进行评估。最后可识别余量（LIM）标记了区分与同化之间的可行性边界。对于确定性诊断图，我们提供精确LIM递归；对于带噪声的有限时域恢复，我们提出风险预算兼容性规划（RBCP），它在硬最坏情况失败约束下搜索兼容性感知前沿。在抽象微服务拓扑上的事件恢复和MiniGrid中的潜在损伤导航中，RBCP在满足失败预算的同时改善了风险可行的恢复。一个假对照——保持模型不兼容的成本匹配动作——完全消除了增益，确认收益来自改变哪些策略对哪些模型可接受，而非来自额外搜索或额外预算。
英文摘要
Under irreversible resource depletion, an agent can spend resources to distinguish among latent fault models, or to change the system state so that the remaining models admit a common acceptable continuation--at which point further diagnosis becomes unnecessary. This distinguish-or-homogenize principle identifies a path that existing frameworks for identification, planning, and diagnosis do not make explicit: prior formulations treat the mapping from fault models to acceptable policies as a given, whereas LCPI makes it a function of the agent's own actions. We formalize this principle through Last-Chance Policy Identification (LCPI), where correctness is evaluated at the state the agent reaches rather than at the initial state. The Last Identifiable Margin (LIM) marks the feasibility boundary between distinguishing and homogenizing. For deterministic diagnostic graphs we provide the Exact-LIM recursion; for noisy finite-horizon recovery we propose Risk-Budgeted Compatibility Planning (RBCP), which searches a compatibility-aware frontier under a hard worst-case failure constraint. Across incident recovery on abstract microservice topologies and latent-damage navigation in MiniGrid, RBCP improves risk-feasible recovery while satisfying the failure budget. A sham control--cost-matched actions that preserve model incompatibility--eliminates the gain entirely, confirming that the benefit comes from changing which policies are acceptable for which models, not from extra search or additional budget.
