SWE-Universe, a scalable and efficient framework for automatically constructing real-world software engineering (SWE) verifiable environments from GitHub pull requests (PRs), utilizes a building agent powered by an efficient custom-trained model to ensure the reliable generation of high-fidelity, verifiable tasks.
Mouxiang Chen, Lei Zhang, Yunlong Feng et al.· arXiv.org· 14 citations· ⚡1
Qwen-CUA is introduced, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone that outperforms Qwen3.7 and remains competitive with leading proprietary systems, and scalable verifiable interaction and hybrid tool use as key directions.
Dunjie Lu, Shuai Bai, Tianyi Bai et al.· 2 citations
These results show that current agents are still far from professional-level computer use: rather than stumbling on basic GUI control or coding, they lose track of constraints, miss information that arrives mid-task, guess rather than ask the user, and skip verification, struggling most when a task hinges on hidden sta...
