Probe-and-Resume: When and How to Evaluate Agent Execution
arXiv:2610.21088v1 Announce Type: new Abstract: Test-time search can improve agent performance by exploring alternative actions and using a critic to select promising branches. We study this approach in terminal-based computer-use...
Read more: https://arxiv.org/abs/2610.21088
Scan with your phone
Scan with your phone