Task Planning on Apple task scenario (Put the apple in the fridge)
8.1Avg Execution Time (s)ZKTP - No Refine
Evaluation results
| Method | Links | |
|---|---|---|
| ZKTP - No RefineRefinement=Disabled2026.01 | 8.1 | |
| BCR2026.01 | 10.2 | |
| ZKTPRefinement=Enabled2026.01 | 18.2 | |
| MLDT2026.01 | 18.3 | |
| SMART-LLM2026.01 | 49.1 |