Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
Paper • 2605.29447 • Published • 18
zhang
mytf
AI & ML interests
None yet
Recent Activity
upvoted a paper 7 days ago
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization liked a dataset about 2 years ago
Oasis-Team/Oasis-CorpusOrganizations
None yet