SOURCE-LINKED INTELLIGENCE

How Many Pixels Is a Digit Worth? Place-Aware Coordinate Entropy for GUI Agent Confidence Estimation

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

GUI agents predict click coordinates as digit-token sequences, but standard text-LLM confidence estimation methods rank correct clicks from wrong ones only weakly. GUI-specific alternatives use K samples or new supervision, but still leave room for improvement. We trace part of this to place-value asymmetry: bounding-box correctness often makes higher-place digits more important than lower-place digits, so uniform aggregation weakens the signal that determines correctness. The fix is to weight each digit's Shannon entropy by its place value. We call this Place-Aware Coordinate Entropy (PACE).

Read original source ↗ Open in workspace

recordType

paper

region

Global