ResearchDatasetsPALADINEVAL, TOOLREFLECTEVAL, API-BANK, and WIKIDATALIVEPALADINEVAL, TOOLREFLECTEVAL, API-BANK, and WIKIDATALIVEFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsTool-use recoveryPALADINEVAL, TOOLREFLECTEVAL, API-BANK, and WIKIDATALIVE (evaluation)—Primary metric0
Tool-use recoveryPALADINEVAL, TOOLREFLECTEVAL, API-BANK, and WIKIDATALIVE (evaluation)—Primary metric0