Beyond Task Completion: Training Capable and Safe Computer-Use Agents
Quick summary
arXiv:2609.22178v2 Announce Type: 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 execution on risk: it should complete ordinary benign tasks, avoid environmental hazards and continue when a safe completion path remains, and refuse when the goal is harmful or no safe path exists. To learn this conditional policy, we develop Safety and Capability Optimization for Policy Execution (SCOPE), w
Key takeaways
- arXiv:2609.22178v2 Announce Type: 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 execution on risk: it should complete ordinary benign tasks, avoid environmental hazards and continue when a safe completion path remains, and refuse when the goal is harmful or no safe path exists.
- To learn this conditional policy, we develop Safety and Capability Optimization for Policy Execution (SCOPE), w
Why it matters
The significance is not only the legal text but how it changes product design. Decisions around “Beyond Task Completion: Training Capable and Safe Computer-Use Agents” may reshape data collection, model training, output accountability and market access.
Member comments