ResearchTasksAgentic AttackAgentic AttackFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedWhisperBench Background execution (held-out)MEMGHOST96.4ISR13Jul 7, 2026WhisperBench Foreground execution (held-out)MEMGHOST98.2ISR8Jul 7, 2026