PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors 事件

PrecisionCUA: Iterative Visual Refinement for Pixel-Precise Cursor Grounding in Code Editors arXiv:2604.13019v2 Announce Type: replace Abstract: 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 (such as VS Code and Cursor), where sub-pixel accuracy is required to interact with dense IDE elements, remains underexplored. Existing approa