IS-Bench：评估由视觉语言模型驱动的具身智能体在日常家务任务中的交互安全性
IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks
AI总结：
IS-Bench通过多模态基准评估视觉语言模型驱动的具身智能体在日常家务任务中的交互安全性，揭示现有智能体缺乏安全意识的问题。
摘要：
由视觉语言模型驱动的具身智能体的规划缺陷带来了显著的安全隐患，阻碍了其在现实世界家务任务中的应用。然而，现有的静态、非交互式评估范式无法充分评估这些交互环境中的风险，因为它们无法模拟从智能体行为中出现的动态风险，并且依赖于不可靠的事后评估，忽略了不安全的中间步骤。为弥合这一关键差距，我们提出了评估智能体的交互安全性：其感知新兴风险并按正确程序顺序执行缓解步骤的能力。因此，我们提出了IS-Bench，第一个多模态基准，专门用于交互安全性，包含161个具有挑战性的场景，388个独特的安全风险在高保真模拟器中实例化。至关重要的是，它促进了新颖的过程导向评估，验证风险缓解行动是否在特定风险步骤之前或之后执行。对领先的VLMs进行的广泛实验，包括GPT-4o和Gemini-2.5系列，揭示了当前智能体缺乏交互安全性意识，尽管安全意识的链式思维可以提高性能，但往往牺牲任务完成。通过突出这些关键限制，IS-Bench为开发更安全、更可靠的具身AI系统提供了基础。代码和数据已发布在https://github.com/AI45Lab/IS-Bench。
英文摘要：
Flawed planning from VLM-driven embodied agents poses significant safety hazards, hindering their deployment in real-world household tasks. However, existing static, non-interactive evaluation paradigms fail to adequately assess risks within these interactive environments, since they cannot simulate dynamic risks that emerge from an agent's actions and rely on unreliable post-hoc evaluations that ignore unsafe intermediate steps. To bridge this critical gap, we propose evaluating an agent's interactive safety: its ability to perceive emergent risks and execute mitigation steps in the correct procedural order. We thus present IS-Bench, the first multi-modal benchmark designed for interactive safety, featuring 161 challenging scenarios with 388 unique safety risks instantiated in a high-fidelity simulator. Crucially, it facilitates a novel process-oriented evaluation that verifies whether risk mitigation actions are performed before/after specific risk-prone steps. Extensive experiments on leading VLMs, including the GPT-4o and Gemini-2.5 series, reveal that current agents lack interactive safety awareness, and that while safety-aware Chain-of-Thought can improve performance, it often compromises task completion. By highlighting these critical limitations, IS-Bench provides a foundation for developing safer and more reliable embodied AI systems. Code and data are released under https://github.com/AI45Lab/IS-Bench.
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。
