Preprint
Oct 2026
SWAP: Stepwise Action Policy Routing for Vision-Language-Action Models
Robot manipulation systems using Vision-Language-Action (VLA) model backbones typically use just one VLA for task execution. However, individual VLAs do not perform well across different task states and environments. We introduce a framework for dynamically composing multiple VLA policies during execution: StepWise Act...
Mousumi Das, Aditeya Prajapati, Abrar Anwar et al.
· 0 citations