以下为上游提供的源文稿，可能存在识别错误。
乔木转写是基于源文稿的中文提炼，不是逐字翻译。请核对原文中的人名、数字与观点。
选一篇，慢慢读
从左侧挑一篇，正文会在这里排成书页。
Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing recursive improvement approaches often rely on self-generated experiences, limiting
阅读原文 · Xinlei Yu, Gen Li, Ji Zhao, Zhangquan Chen, Congcong Wang, Shuai Dong, Zelin Peng, Yuqi Xu, Hongrui Wu, Kaiwen Tuo, Cheng Yang, Kaituo Feng, Yifan Wu, Jiayi Zhang, Dongming Wu, Wenqi Shao, Jiaqi Wang, Xiangyu Yue
向阳乔木 · deepseek-v4-1-flash-261017
这篇论文值得看的地方，在于它想解决 Computer-use Agent 训练里最脏最累的活：数据从哪来、怎么保证可控和可验证、怎么让模型一轮轮变强而不是原地打转。 摘要里报出的数字挺硬：CUA-Master-27B 在 OSWorld Verified 上拿到 80.2，OSWorld 2.0 是 36.9，WeaveBench 43.9，Agents'...