ResearchTasksSister TasksSister TasksFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedextended tau-Bench Retail domainPolicyBank83Pass@1 Rate10Apr 20, 2026extended tau-Bench Airline domainPolicyBank74Pass@1 Rate10Apr 20, 2026