ResearchDatasetsGUIrillaFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAgentic UI InteractionGUIRILLA-TASK agentic12.5Input Success Rate8Element LocalizationGUIrilla-Task (test)65.5Communication Accuracy7