ResearchTasksStateful Agent Backdoor Attack EvaluationStateful Agent Backdoor Attack EvaluationFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedNote-based instantiation 20 episodesLlama-3.1-8B100Initial Success Rate (R_init)4May 8, 2026