ResearchTasksContext SelectionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedLongMemEval session-level (test)TF-IDF0.649F1 Score8Feb 26, 2026LoCoMo turn-level (test)ECS26.5F1 Score6Feb 26, 2026IntraSkill-Bench full 1,975 queriesFull-document prompt82.23Sufficiency (%)5Jun 2, 2026