IG-RFT: An Interaction-Guided RL Framework for VLA Models in Long-Horizon Robotic Manipulation

作者：ARXIV PREPRINT, Zhian Su, Weijie Kong, Haonan Dong, Huixu Dong, Member · 单位：Grasp Laboratory, Mechanical Engineering Department, Zhejiang University · 会议/期刊：arXiv · 日期：2026-02-24 · 来源：Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with RL