A new benchmark with 5,318 GUI tasks, including 200 abnormal ones, shows that state-of-the-art GUI agents degrade sharply when real-world anomalies appear.
SeeClick: Harnessing GUI grounding for advanced visual GUI agents
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
GUI-Robust: A Comprehensive Dataset for Testing GUI Agent Robustness in Real-World Anomalies
A new benchmark with 5,318 GUI tasks, including 200 abnormal ones, shows that state-of-the-art GUI agents degrade sharply when real-world anomalies appear.