ResearchDatasetsToolQAToolQAFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTool-use ReasoningToolQA47.97Accuracy20Tool-based Question AnsweringToolQA hard63Accuracy (Yelp)17Tool-use Question AnsweringToolQA Easy 1.090Yelp Acc17Skill retrievalToolQA56.4nDCG@111