ResearchDatasetsAndroid In The WildAndroid In The WildFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMobile AutomationAndroid In The Wild (AITW)7.7Average Score21Multimodal GUI-agent action executionAndroid in the Wild (AITW) held-out 500-example (test)6.6AITW Accuracy3
Multimodal GUI-agent action executionAndroid in the Wild (AITW) held-out 500-example (test)6.6AITW Accuracy3