ResearchTasksInteractive Instruction FollowingFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedALFWorld UnseenCOMAP86.68Success Rate54Jun 19, 2026ALFWorld OODTask-Perturbed NLL Optimization92Success Rate13Jun 26, 2026ALFWorld (train)ProcMEM90Success Rate9Feb 26, 2026