VLA-RFT: Vision-Language-Action Reinforcement Fine-Tuning with Verified Rewards in World Simulators

作者：Hengtao Li, Pengxiang Ding, Runze Suo, Yihao Wang, Zirui Ge, Dongyuan Zang, Kexian Yu, Mingyang Sun, Hongyin Zhang, Donglin Wang, Weihua Su · 单位：Westlake University, Zhejiang University, Fudan University, Zhengzhou University, Hebei University of Technology · 会议/期刊：arXiv preprint 2025 · 方向：自探索数据采集 · 发布日期：2025-10-01