Evolve Vision-Language-Action Model into an Agent with On-the-fly Tool-use
ART is a tool-injection framework that tunes any VLA model to leverage off-the-shelf tool modules for low-level vision, high-level affordance, and embodiment enhancement, and ART reduces the complexity of the action solution space through tool-use, which improves generalizability across different tasks but also reduces...
Ding-Ge Yi, Yanzhao Yu, Xi-Li Dai et al.
· 1 citation