Beyond Task Completion: Training Capable and Safe Computer-Use Agents

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.22178v2 Announce Type: replace-cross Abstract: 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…

science

Sources

• T1Beyond Task Completion: Training Capable and Safe Computer-Use AgentsarXiv24 Sept, 04:00