AutoGUI-v2 is a new benchmark exposing that VLMs handle basic GUI grounding but struggle with complex interaction logic and state prediction.
If an overlap is detected, one element (typically the one with the larger area) is removed, and the check is repeated until no overlaps remain
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark
AutoGUI-v2 is a new benchmark exposing that VLMs handle basic GUI grounding but struggle with complex interaction logic and state prediction.