VLA2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation

作者：Han Zhao, Jiaxuan Zhang, Wenxuan Song, Pengxiang Ding, Donglin Wang · 单位：Zhejiang University, China MiLAB, Westlake University, China, Southern University of Science and Technology, China, Hong Kong University of Science and Technology (Guangzhou), China · 会议/期刊：arXiv · 日期：2025-10-16 · 来源：Bottlenecks / Generalization / Agent