ResearchTasksMulti-agent Task FulfillmentMulti-agent Task FulfillmentFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedAWS Benchmark Mortgage scenarioSEAgent62.07Goal Success Rate (User)2Feb 26, 2026AWS Benchmark Travel scenarioSEAgent78.79User GSR2Feb 26, 2026