ResearchDatasetsA3S-BenchA3S-BenchFollowBenchmarksTaskDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyTaskDatasetSOTA resultTrendResultsAgent SecurityA3S-BENCH Advanced 1.019.68RTR@111Agent SecurityA3S-BENCH Basic 1.045.27RTR@1 (%)11Autonomous agent security evaluationA3S-Bench—Primary metric0