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。
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-quality delivery on complex productivity tasks and continued monitoring and decision-making over long horizons, a combina
阅读原文 · Jiajie Jin, Guanting Dong, Chengjun Pan, Xin Deng, Zhuohui Sheng, Guoqiang Wang, Tao Gui, Yutao Zhu, Yujia Chen, Shihong Yi, Binze Hu, Zhixiong Yang, Zhichao Sun, Rui Wang, Han Han, Mingyu Ma, Junhao Huang, Xiaotao Wang, Huicheng Jiang, Yuyang Hu, Xinyu Yang, Wanghan Xu, Yajie Yang, Zhecan Wang, Honglin Guo, Xiaoyu Xing, Xiaoqian Zhang, Yulun Zhu, Xiaoxi Li, Jiahang Lin, Shaofan Liu, Shihan Dou, Zhiheng Xi, Qi Zhang, Yu-Gang Jiang, See-Kiong Ng, Yang Zhang, Tat-Seng Chua, Ji-Rong Wen, Zhicheng Dou
向阳乔木 · deepseek-v4-1-flash-261017
这篇论文值得看的地方，在于它试图回答一个很实际的问题：当 AI 要真正参与生产力工作，比如写代码、做设计、改 CAD 模型、调 Blender 场景，光“单轮对话答得好”远远不够。 真正难的是 长周期 。任务要跨越多天、多次会话，中间可能中断、可能换人接手、可能人和 AI 同时改同一份文件。CoworkOS 想搭的就是这套“让 AI 能持续干活”的运行时底座...