ResearchDatasetscageFollowBenchmarksTask NameDataset NameSOTA MethodSortMost resultsRecently updatedMost papersApplyTask NameDataset NameSOTA ResultTrendResultsAgent Return VolatilityCAGE-2 v1 (test)2SD40Single-arm motion planningcage single-arm planning scene96Success Rate9unconstrained single-arm planningcage scenario95Success Rate9Red Teaming EvaluationCAGE 200 episodes 43.74AHD6Cyber Red TeamingCAGE 4 (200 episodes)9.86AHD4