Probe-and-Resume: When and How to Evaluate Agent Execution
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 environments, which expose only a partial view of a large underlying state, and find that the Monte Carlo tree search (MCTS) configuratio...
Jia-Kai Xu, Tian-Cheng Ge, Tu-Jie Guan et al.
· 0 citations