Cooperative Adaptive Cruise Control on CACC Catch-up scenario
1.212RMSE (Lateral)MACRO-LLM
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| MACRO-LLMbackbone=gpt-4o-2024-08-06, sampling temperature=0.3, top-p=12026.01 | 1.212 | 0.897 | 0.455 | 0.283 | |
| DPPOparadigm=MARL2026.01 | 1.603 | 0.978 | 0.994 | 0.474 | |
| LAMENparadigm=LLM-based MAS2026.01 | 1.891 | 0.648 | 3.32 | 0.601 | |
| DMPOparadigm=MARL2026.01 | 4.765 | 0.534 | 3.025 | 1.349 | |
| ChatEvalparadigm=LLM-based MAS2026.01 | 5.495 | 2.113 | 2.947 | 1.241 | |
| ToM-Beliefparadigm=LLM-based MAS2026.01 | 5.514 | 4.409 | 4.002 | 3.13 | |
| IC3Netparadigm=MARL2026.01 | 8.687 | 4.205 | 7.232 | 3.399 |