ResearchDatasetstau2-bench, SkillsBench, and ALFWorldtau2-bench, SkillsBench, and ALFWorldFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAgent Task Completiontau2-bench, SkillsBench, and ALFWorld Average58.7Average Pass Rate9