ResearchTasksDelegation ReconstructionFollowBenchmarksDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyDataset NameSOTA methodMetricTrendResultsLast UpdatedSynthetic Workflow trial-and-adapt W3B0 (trace-only)1Ambiguity (median)4Jun 9, 2026Synthetic Workflow W2 multi-agent compositionB2 (best-effort hybrid)107,718Ambiguity Resolution (Median)4Jun 9, 2026Synthetic Workflow W1 cross-systemB0 (trace-only)1Ambiguity (median)4Jun 9, 2026
Synthetic Workflow W2 multi-agent compositionB2 (best-effort hybrid)107,718Ambiguity Resolution (Median)4Jun 9, 2026