ResearchTasksRole-playing Quality EvaluationRole-playing Quality EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedRoleMemo (test)DUALMEM-RL4.22Information Richness14May 26, 2026RoleChat (Human Evaluation)RoleJudge87Win Rate2Apr 16, 2026