ResearchDatasetsWebVoyager, Online-Mind2Web, DeepShopWebVoyager, Online-Mind2Web, DeepShopFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsGUI agent successWebVoyager, Online-Mind2Web, DeepShop (test average)69.3Average Success Rate17