RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents
[Przetwarzanie języka] Autorzy: Shuai Bai, Jiayong Deng, Yikun Fu i 29 więcej
Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs that autonomously decide when to explore an interface, implement software, and run and visually verify their artifacts. We introduce RecreationWorld, a five-platform framework built around recreation: given a running reference, an agent must discover its behavior and build a faithful implementation with no prescribed workflow. RecreationWorld provides reproducible environments on Ubuntu, macOS, Windows, Android, and Web, plus a unified harness with native GUI control and coding tools. The running reference serves as an oracle for hidden behavioral tests, providing execution-grounded rewards. We scale trajectory generation with high-quality open…
- Kategoria arxiv
- cs.CL
- Kategoria
- Przetwarzanie języka