Atomic-Probe Governance for Skill Updates in Compositional Robot Policies

ArXi:2604.26689v1 Announce Type: cross Skill libraries in deployed robotic systems are continually updated through fine-tuning, fresh nstrations, or domain adaptation, yet existing typed-composition methods (BLADE, SymSkill, Generative Skill Chaining) treat the library as frozen at test time and do not analyze how composition outcomes change when a skill is replaced. We