ResearchTasksMulti-agent policy synthesisFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedCleanupGemini 3.1 Pro2.75U Score9Mar 23, 2026GatheringGemini 3.1 Pro4.59Metric U9Mar 23, 2026