ResearchTasksMulti-agent planning and executionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedMAT2-THOR Overall TasksScale Plan78TCR5Mar 11, 2026MAT2-THOR Vague TasksScale Plan71Task Completion Rate (TCR)5Mar 11, 2026MAT2-THOR Complex TasksScale Plan59TCR5Mar 11, 2026MAT2-THOR Simple TasksScale Plan92TCR5Mar 11, 2026