Multi-agent coordination on Overcooked-AI
122.3Coordination Ring ScoreAgents
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| AgentsCategory=Static-Prompting2026.04 | 122.3 | 118.5 | 202.7 | 68.4 | 43.6 | |
| AutoPECategory=Self-Evolving2026.04 | 133.4 | 122.8 | 143.5 | 71.9 | 38.2 | |
| CoTCategory=Static-Prompting2026.04 | 140 | 126.7 | 226.7 | 73.3 | 40 | |
| PBT2024.06 | 141.328 | — | — | — | — | |
| DSPyCategory=Self-Evolving2026.04 | 141.4 | 145.7 | 217.3 | 62.1 | 52.4 | |
| SymbolicCategory=Self-Evolving2026.04 | 148.5 | 147.5 | 232.4 | 104.2 | 55.1 | |
| ReflexionCategory=Self-Evolving2026.04 | 157.8 | 151.1 | 204.1 | 138.5 | 68.7 | |
| TextGradCategory=Self-Evolving2026.04 | 163.8 | 131.3 | 230.6 | 85.3 | 54.5 | |
| ProAgent2024.06 | 175.329 | — | 228.723 | — | — | |
| LangMARLCategory=Ours2026.04 | 184.4 | 171.4 | 244.4 | 148.9 | 77.8 | |
| COLE2024.06 | — | — | — | 2,421.8 | — | |
| MEP2024.06 | — | 18,515 | — | — | — | |
| VillagerAgent2024.06 | — | — | 3,048.76 | 12,016.97 | 1,484.38 |