Robotic Task Planning on VirtualHome v2.3.0
41.9GCRCLMASP-Clingo
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CLMASP-ClingoLLM=GPT-4o2024.06 | 41.9 | 86.99 | |
| CLMASP-ClingoLLM=GPT-3.52024.06 | 37.07 | 89.59 | |
| Mu et al., 2024LLM=Llama-3.1, Fine-tuned=true2024.06 | 26.73 | 32.71 | |
| Singh et al., 2023LLM=GPT-4o2024.06 | 21.7 | 13.75 | |
| Singh et al., 2023LLM=GPT-3.52024.06 | 20.42 | 16.67 | |
| CLMASP-ClingoLLM=Llama-3.12024.06 | 13.69 | 81.04 | |
| Huang et al., 2022LLM=GPT-4o2024.06 | 9.94 | 11.9 | |
| Huang et al., 2022LLM=GPT-3.52024.06 | 6.27 | 9.29 |