AIBullisharXiv – CS AI · 10h ago7/10
🧠
NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning
Researchers introduce NEXUS, a framework enabling embodied AI agents to learn symbolic constraints for safer decision-making in physical environments. The system addresses the gap between probabilistic language models and the deterministic safety requirements of robotics by decoupling physical feasibility from safety specifications, achieving improved task success while refusing unsafe instructions.