AI RESEARCH
See, Point, Refine: Multi-Turn Approach to GUI Grounding with Visual Feedback
arXiv CS.CV
•
ArXi:2604.13019v1 Announce Type: new Computer Use Agents (CUAs) fundamentally rely on graphical user interface (GUI) grounding to translate language instructions into executable screen actions, but editing-level grounding in dense coding interfaces, where sub-pixel accuracy is required to interact with dense IDE elements, remains underexplored. Existing approaches typically rely on single-shot coordinate prediction, which lacks a mechanism for error correction and often fails in high-density interfaces.