ResearchTasksPolicy ReferralPolicy ReferralFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedGTAPolicyTriMPI9.45GTAPolicy Score5Apr 21, 2026ClevrPolicyTriMPI6.26ClevrPolicy-T Score5Apr 21, 2026