CoworkOS提出面向长周期智能体工作的框架
Jiajie Jin等40位作者于2026年11月2日向arXiv提交CoworkOS论文。作者将其描述为一种面向长周期工作的通用框架，将模型驱动的任务策略与运行时执行管理分离，并支持同步或异步委派给子智能体、层级化工作区、持久化语义记忆，以及人类和智能体共同修改文档、演示文稿、CAD模型和Blender场景等共享成果。作者称，CoworkOS在12项基准和6类真实应用中的表现可与Codex和DeepSeek Harness竞争。
该提案通过结合人机协同、共享演进成果、任务委派、持久化语义记忆和中断后可恢复的工作，回应长周期生产力任务的需求。
Computer Science > Artificial Intelligence
arXiv:2611.03178 (cs)
[Submitted on 2 Nov 2026]
Title:CoworkOS:Scaling Agent Coworkers for Real-world Automation
Authors: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
View a PDF of the paper titled CoworkOS:Scaling Agent Coworkers for Real-world Automation, by Jiajie Jin and 39 other authors