ResearchTasksVLM Agent Success Rate EstimationVLM Agent Success Rate EstimationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedEZPointsGiGPO100Success Rate4Jul 7, 2026Sokoban 6x6STAPO80.5Success Rate4Jul 7, 2026