AI RESEARCH

EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents

arXiv CS.CL

ArXi:2605.30924v1 Announce Type: new MLLM-powered embodied agents deployed in real-world environments encounter physical hazards. However, existing approaches lack explicit mechanisms for identifying hazards and reasoning about action-conditioned risks, leading agents to either miss risky interactions or over-identify risks. To address this, we propose EMBGuard, the first MLLM-based safety guardrail for embodied agents designed to decouple physical risk reasoning from agent policy.