CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents 文章

ArXiv CS.AI2026-05-26NEWSen作者: Bowen Wang, Dunjie Lu, Junli Wang, Tianyi Bai, Shixuan Liu, Zhipeng Zhang, Haiquan Wang, Hao Hu, Tianbao Xie, Shuai Bai, Dayiheng Liu, Que Shen, Junyang Lin, Tao Yu

查看原文 →

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents · 相关技术

相关技术

NAT gin 远程代码执行（RCE）研究法辛烷值 reward function reinforcement learning exec UCT Tera Straight-Through Estimator Scala Reinforcement learning with verifiable rewards RLVR LMM For ANN Agent Table