ResearchDatasetsExperimental RunsExperimental RunsFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsWorkflow Completion600 experimental runs 50 runs x 4 scenarios x 3 frameworks100Completion Rate5Conflict Detection600 Experimental Runs 50 runs x 4 scenarios x 3 frameworks25.9Conflict Rate5