arXiv 2610.26828 · cs.AI · 2026-10-19
Agent World Model in the Wild: Computer-Use Agent Environment Synthesis
Zhaoyang Wang, Qianhui Wu, Haorui Wang, Simon Yu, Baolin Peng, Canwen Xu, Hao Cheng, Wenlin Yao and 4 more
Microsoft Research
In latest · #68 Added on 2026-10-23
One-line takeaway
Microsoft Research’s WildAWM synthesises executable computer-use environments and tasks with open-source models, each supporting GUI, MCP services and CLI together, to train general computer-use agents without the risks of training on real systems.
微软研究院的 WildAWM 用开源模型批量合成可执行的电脑操作环境与任务，同一环境同时支持图形界面、MCP 服务和命令行，用于训练通用电脑操作智能体，避免直接在真实系统上训练的安全风险。
Read on arXiv PDF Hugging Face discussion Code Project page
Topics & disciplines
More on Agents
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲388
- Player-1: Learning to Play from Synthetic Experience ▲347
More on Code & SWE
- MaLiang-Harness: A Programmable Path to Image and Video Generation 2026-09-28 · ▲367
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use 2026-10-15 · ▲325
- HexaShell: A Thin Harness for Exploring the Limits of VLM Agents as Robot Coding Agents 2026-10-16 · ▲294
- AgentSWE: Can Coding Agents Build the Agent You Actually Want? 2026-10-09 · ▲233
- CodeMidas: Scaling Agentic Coding RL Environments from Code Itself 2026-09-18 · ▲138
More from Microsoft Research
About this data
Metadata from the arXiv API (verified); upvotes from Hugging Face Daily Papers; citations from Semantic Scholar. Last refreshed 2026-10-26.
The takeaway is written by AIMap from the abstract; the abstract itself is not reproduced — read the original.