Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
Paper • 2605.29447 • Published • 21
pupudi
pupudi
AI & ML interests
None yet
Recent Activity
upvoted a paper 26 days ago
Long Live The Balance: Information Bottleneck Driven Tree-based Policy OptimizationOrganizations
None yet
upvoted a paper 25 days ago