ResearchDatasetsAgentic Skill-UseAgentic Skill-UseFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAgentic Skill-UseAgentic Skill-Use Gold + Distr.80Final Success Rate7Agentic Skill-UseAgentic Skill-Use Gold Skills88Final Score7Agentic Skill-UseAgentic Skill-Use No Skills24Final Score7