ResearchDatasetsRoTBenchFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsTool UseRoTBench Multi-turn72.9Tool Selection Accuracy35Tool UseRoTBench Single-turn84.8Tool Selection35Robustness of Tool-useRoTBench78.76TS27