ResearchDatasetsAGENTIFAGENTIFFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsInstruction FollowingAgentIF66.1CSR29Instruction FollowingAgentIF (Out-of-Domain)66.9CSR23Constraint RecallAGENTIF long-horizon agentic conversations47.4Constraint Recall6