ResearchTasksAction and Reason PredictionAction and Reason PredictionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedBDD-OIA (test)NLE-DM72.3Mean F1 (Action)9May 4, 2026nu-AR (test)OIA73.8F1 Mean Action3May 4, 2026