ICAT：基于事件-案例的自适应测试用于体素世界模型中的物理风险预测
ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
AI总结：
ICAT通过结合真实事故报告和安全手册构建结构化风险记忆，约束生成具有因果链和严重程度标签的风险案例，提升体素世界模型在物理风险预测中的可靠性。
摘要：
视频生成的世界模型越来越多地被用作神经模拟器用于具身规划和策略学习，但其预测物理风险和严重后果的能力很少被评估。我们发现这些模型常常低估或省略关键危险提示和严重后果，这可能导致在规划和训练时产生不安全的偏好。我们提出了ICAT，通过构建结构化风险记忆并检索/组合它们，将测试扎根于真实事故报告和安全手册，以约束生成具有因果链和严重程度标签的风险案例。在基于ICAT的基准测试中，主流世界模型经常遗漏机制和触发条件，并错误校准严重程度，无法满足安全关键的具身部署所需的可靠性。
英文摘要：
Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions, which can induce unsafe preferences during planning and training on imagined rollouts. We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories and retrieving/composing them to constrain the generation of risk cases with causal chains and severity labels. Experiments on an ICAT-based benchmark show that mainstream world models frequently miss mechanisms and triggering conditions and miscalibrate severity, falling short of the reliability required for safety-critical embodied deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
