SOURCE-LINKED INTELLIGENCE

Safe Task Planning with Long-Term Graph Memory for Embodied Agents

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Large language models (LLMs) and vision-language models (VLMs) have significantly advanced zero-shot task planning for embodied agents. However, most LLM- and VLM-driven methods struggle to generate safe high-level actions due to a lack of physical risk awareness, particularly under partial observability, where hazards lie outside the immediate field of view. To address this challenge, we propose a novel safe task-planning framework, SafeMem, which constructs and maintains a long-term semantic graph memory of the open and dynamic environment. Based on egocentric observations, the proposed fram

Read original source ↗ Open in workspace

recordType

paper

region

Global