NEXUS framework enables continual learning of symbolic constraints for embodied planning by decoupling physical feasibility from safety specifications, achieving higher task success, refusal of unsafe commands, and defense against attacks on SafeAgentBench.
imply". •Correct: (imply (openable garbagecan) (isOpen garbagecan)) •NEVER use
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
NEXUS: Continual Learning of Symbolic Constraints for Safe and Robust Embodied Planning
NEXUS framework enables continual learning of symbolic constraints for embodied planning by decoupling physical feasibility from safety specifications, achieving higher task success, refusal of unsafe commands, and defense against attacks on SafeAgentBench.