Multi-agent collaboration reasoning on PDDP
64.4AccuracySTRMAC
Evaluation results
| Method | Links | ||
|---|---|---|---|
| STRMACModel=GPT-4o2025.11 | 64.4 | 756.3 | |
| IG-MASModel=GPT-4o2025.11 | 63.4 | 6,322.9 | |
| MACNETModel=GPT-4o2025.11 | 57.7 | 2,826.4 | |
| Random-ChainModel=GPT-4o2025.11 | 56.6 | 7,934.3 | |
| MDAgentsModel=GPT-4o2025.11 | 54.6 | 79,759.8 | |
| LLM-DebateModel=GPT-4o2025.11 | 53.6 | 23,901 | |
| MOAModel=GPT-4o2025.11 | 53.1 | 14,236.6 |