Self-Evolving Just-In-Time Memory Enables Proactive Safety in Embodied Agents
A new framework called Self-Evolving Just-In-Time Memory has been proposed to improve safety in embodied agents, such as household robots, by shifting from traditional guardrails that can stall progress to proactive hazard mitigation. The framework introduces components like a Risk-Sufficient Topological Belief Graph, Agency-Grounded Factual Memory, and Experience Memory with procedural Meta-Skills. Experiments on the IS-Bench benchmark show a 30.3% increase in Safe-Success rate for the Qwen3-VL-8B model, indicating more effective hazard mitigation without sacrificing task completion.
Why it matters: This work offers a significant advance in embodied agent safety by enabling proactive hazard mitigation that maintains task efficiency, addressing a key limitation of existing safety approaches.
Full story at: arXiv Machine Learning ↗