arXiv · cs.AI · 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 · 7 小时前模型评分61
CoworkOS 发布：面向长周期任务的智能体协作框架
CoworkOS:Scaling Agent Coworkers for Real-world Automation
导读
研究团队提出 CoworkOS，一个把任务策略与执行管理分开的长周期工作框架，由模型决定动作、委派与验收，运行时维护状态和反馈。该框架采用三层架构，支持直接执行或同步、异步委派给子智能体，人类与智能体可在共享应用层查看并修改同一份文档、演示、CAD 模型和 Blender 场景。
分类置信度
中 · 待人工复核
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
事件类型：研究发布
证据摘录
- “We introduce CoworkOS, a general-purpose harness for long-horizon work that separates task strategy from execution management: the model decides actions, delegation, and acceptance, while the runtime maintains state and feedback.”
来源：arXiv · cs.AI · arxiv.org