Traveling Salesperson Problem (ACO) on TSP-ACO N=100 (val)
7.784Mean Tour LengthOptimal
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Optimal2026.05 | 7.784 | 0 | |
| AHD Agent w/SRModel=Qwen3-4B-Instruct-2507, Eval=100, Cost ($)=0.0312026.05 | 8.342 | 7.118 | |
| AHD AgentModel=Qwen3-4B-Instruct-2507, Eval=11.8, Cost ($)=0.0032026.05 | 8.345 | 7.195 | |
| ReEvoModel=DeepSeek-V4-Flash, Eval=100, Cost ($)=0.0512026.05 | 8.35 | 7.255 | |
| MCTS-AHDModel=GPT-4o, Eval=100, Cost ($)=1.0262026.05 | 8.365 | 8.536 | |
| AHD AgentModel=DeepSeek-V4-Flash, Eval=14.2, Cost ($)=0.0612026.05 | 8.389 | 7.766 | |
| EOHModel=GPT-4o, Eval=100, Cost ($)=0.2362026.05 | 8.412 | 8.057 | |
| EOHModel=DeepSeek-V4-Flash, Eval=100, Cost ($)=0.0132026.05 | 8.473 | 8.839 | |
| MCTS-AHDModel=DeepSeek-V4-Flash, Eval=100, Cost ($)=0.1042026.05 | 8.475 | 8.863 | |
| CALMModel=Qwen3-4B-Instruct-2507, Eval=150, Cost ($)=0.0692026.05 | 8.607 | 10.555 | |
| ReEvoModel=GPT-4o, Eval=100, Cost ($)=0.4732026.05 | 8.669 | 11.358 | |
| AHD AgentModel=GPT-4o, Eval=7, Cost ($)=0.0582026.05 | 8.893 | 14.847 | |
| Baseline heuristic2026.05 | 10.081 | 29.503 |