benchmarks evals
A Click’s Most Important Digit Carried the Warning
Place-weighted coordinate uncertainty improved GUI-agent confidence estimates.
Summary
Place-weighted coordinate uncertainty improved GUI-agent confidence estimates.
GUI agents emit click coordinates as digit tokens, but uncertainty in the leading digits can matter much more than uncertainty in later digits when a click must land inside a target box. A new method, Place-Aware Coordinate Entropy, weights each digit's entropy by its place value. On ScreenSpot-Pro and ScreenSpot-v2 with fixed-scale agents, it improved both error ranking and selective accuracy across the authors' primary comparisons in one forward pass, matching or beating some methods that sample multiple clicks. The result concerns benchmark click confidence, not general reliability across all user interfaces.
Why it matters
Place-weighted coordinate uncertainty improved GUI-agent confidence estimates.
Limits and context
- The result concerns benchmark click confidence, not general reliability across all user interfaces.
Key claims
Place-weighted coordinate uncertainty improved GUI-agent confidence estimates.
Qualification: The result concerns benchmark click confidence, not general reliability across all user interfaces.
Evidence: source-2026-09-22-005
Sources
- arXiv preprint 2609.24277arXiv · primary research
Corrections
No corrections have been recorded for this story.