| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Agent Return Volatility | CAGE-2 v1 (test) | SD2 | 40 | |
| Single-arm motion planning | cage single-arm planning scene | Success Rate96 | 9 | |
| unconstrained single-arm planning | cage scenario | Success Rate95 | 9 | |
| Red Teaming Evaluation | CAGE 200 episodes 4 | AHD3.74 | 6 | |
| Cyber Red Teaming | CAGE 4 (200 episodes) | AHD9.86 | 4 |