ResearchTasksRuntime Agent MemoryFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedHotpotQABudgetMem-CAP58.7F1 Score20Feb 26, 2026LongMemEvalBudgetMem-REA40.53F1 Score20Feb 26, 2026LoCoMoBudgetMem-CAP43.05F1 Score20Feb 26, 2026