A11y-Compressor: A Framework for Enhancing the Efficiency of GUI Agent Observations through Visual Context Reconstruction and Redundancy Reduction

arXiv:2605.00551v1 Announce Type: cross Abstract: AI agents that interact with graphical user interfaces (GUIs) require effective observation representations for reliable grounding. The accessibility tree is a commonly used text-based format that encodes UI element attributes, but it suffers from...