AI RESEARCH

AutoFocus: Uncertainty-Aware Active Visual Search for GUI Grounding

arXiv CS.CV

ArXi:2605.02630v1 Announce Type: new Vision-Language Models (VLMs) have enabled autonomous GUI agents that translate natural language instructions into executable screen coordinates. However, grounding performance degrades in high-resolution interfaces, where dense layouts and small interactive elements expose a resolution gap between modern displays and model input constraints.