ResearchDatasetsMindGames ArenaMindGames ArenaFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsMulti-agent strategic interactionMindGames Arena Efficient Track (Stage 2)34.2TrueSkill Rating5Competitive Game PlayingMindGames Arena Open Track, Stage 238TrueSkill Score5Social Deduction GameMindGames Arena Social Deduction Track13.9TrueSkill Rating3