CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents 事件

CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents arXiv:2605.25624v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agents (CUAs) has been bottlenecked by the scarcity of scalable training data with deterministic rewards. Constructing such data for CUAs requires consistent task instruction, executable enviro