Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
Paper • 2605.29447 • Published • 20
haozhou
hao36918
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 10 days ago
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization upvoted a paper 3 months ago
MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language ModelsOrganizations
