CoworkOS：面向真实世界自动化的长周期协作智能体框架
CoworkOS:Scaling Agent Coworkers for Real-world Automation
论文提出 CoworkOS，一个把任务策略与执行管理分离的通用长周期工作框架，由模型决定行动、委派与验收，运行时维护状态和反馈。其三层架构支持同步或异步委派给 Subagent，人类与智能体可通过共享应用层共同查看和修改同一份文档、演示、CAD 模型与 Blender 场景，并借助分层工作区和持久语义记忆实现跨会话续接。
Computer Science > Artificial Intelligence
arXiv:2611.03178 (cs)
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
Abstract: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 combination that remains an open challenge. 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. Its three-layer architecture enables direct execution or delegation to Subagents, synchronously or asynchronously, under stable responsibilities. Through a shared application layer, humans and agents inspect and revise the same evolving documents, presentations, CAD models, and Blender scenes, so human-in-the-loop participation can enter both through conversation and through direct modification of the work itself. To sustain continuity across agents and sessions, CoworkOS further introduces hierarchical workspaces and persistent semantic memory, so working files, key decisions, and long-running Job logs remain shareable, reusable, and resumable after interruption. Across 12 benchmarks and 6 categories of real-world applications, CoworkOS proves highly competitive with frontier agent applications such as Codex and DeepSeek Harness. As a sustained-work case study, CoworkOS uses GLM-5.3 as its backbone to conduct RSI-driven automated post-training on Qwen3.6-35B-A3B. Over five rounds, the model's average score across eight benchmarks rose from 33.19 to 42.95 (+9.76). Looking ahead, we believe CoworkOS opens a meaningful path toward general cowork-agent intelligence.
| Comments: | 34 pages |
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.03178 [cs.AI] |
| (or arXiv:2611.03178v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.03178 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jiajie Jin [view email]
[v1]
Mon, 2 Nov 2026 14:15:11 UTC (25,551 KB)
Current browse context:
cs.AI
Change to browse by:
Bookmark
Bibliographic and Citation Tools
Code, Data and Media Associated with this Article
Demos
Recommenders and Search Tools
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
来源：arXiv cs.CL · arxiv.org