ResearchTasksMulti-Agent Reinforcement Learning training efficiencyMulti-Agent Reinforcement Learning training efficiencyFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedCategory Assistant (CA) (train)FlexMARL78.8E2E Training Time (s)4Feb 26, 2026Merchant Assistant (MA) (train)FlexMARL126.1E2E Time (s)4Feb 26, 2026