Beyond Task Completion: Training Capable and Safe Computer-Use Agents
Computer-use agents (CUAs) have made rapid progress in completing complex tasks through graphical user interfaces, yet post-training centered on task success alone does not induce reliable safety behavior. A reliable CUA must condition its execution on risk: it should complete ordinary benign tasks, avoid environmental...
Zeng Kang, Zhen-Yun Yin, Yang Zhang et al.
· 0 citations