Multi-Agent Reinforcement Learning (MARL) is increasingly deployed in safety-critical domains, yet methods for interpretable failure detection and attribution remain underdeveloped. We introduce a two-stage gradient-based framework that provides interpretable diagnostics for three critical failure analysis tasks: (1) detecting the true initial failure source (Patient-0); (2) validating why non-attacked agents may be flagged first due to domino effects; and (3) tracing how failures propagate through learned coordination pathways. Stage 1 performs interpretable per-agent failure detection via Taylor-remainder analysis of policy-gradient costs, declaring an initial Patient-0 candidate at the first threshold crossing. Stage 2 provides validation through geometric analysis of critic derivatives-first-order sensitivity and directional second-order curvature aggregated over causal windows to construct interpretable contagion graphs. This approach explains "downstream-first" detection anomalies by revealing pathways that amplify upstream deviations. Evaluated across 500 episodes in Simple Spread (3 and 5 agents) and 100 episodes in StarCraft II using MADDPG and HATRPO, our method achieves 88.2-99.4% Patient-0 detection accuracy while providing interpretable geometric evidence for detection decisions. By moving beyond black-box detection to interpretable gradient-level forensics, this framework offers practical tools for diagnosing cascading failures in safety-critical MARL systems.

翻译：多智能体强化学习（MARL）正日益部署在安全关键领域，然而用于可解释故障检测与归因的方法仍不成熟。本文提出一种基于梯度的两阶段框架，为三项关键故障分析任务提供可解释的诊断：（1）检测真实初始故障源（零号患者）；（2）验证因连锁效应导致非受攻击智能体首先被标记的原因；（3）追踪故障如何通过学习到的协调路径传播。第一阶段通过策略梯度成本的泰勒余项分析实现可解释的逐智能体故障检测，在首次阈值跨越时声明初始零号患者候选。第二阶段通过评论家导数的几何分析——聚合因果窗口内的一阶敏感性与方向二阶曲率——构建可解释的传播图以提供验证。该方法通过揭示放大上游偏差的路径，解释了"下游优先"检测异常现象。在Simple Spread（3智能体与5智能体）的500个回合和StarCraft II的100个回合中，使用MADDPG与HATRPO算法进行评估，本方法实现了88.2-99.4%的零号患者检测准确率，同时为检测决策提供可解释的几何证据。该框架通过超越黑盒检测，实现可解释的梯度级取证分析，为安全关键MARL系统中的级联故障诊断提供了实用工具。