Task Planning on Mug task scenario Soak the mug
10.9Average Execution Time (s)MLDT
Evaluation results
| Method | Links | |
|---|---|---|
| MLDT2026.01 | 10.9 | |
| ZKTP - No RefineRefinement=Disabled2026.01 | 28.9 | |
| BCR2026.01 | 45.9 | |
| SMART-LLM2026.01 | 61.2 | |
| ZKTPRefinement=Enabled2026.01 | 88.5 |