| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Simulator selection | Supply Chain | Top-1 Regret0.24 | 24 | |
| Policy Selection | Supply Chain | Precision@397 | 24 | |
| Mechanism-grounded reasoning | Supply Chain | Completeness4.6 | 12 | |
| Creativity Evaluation | Supply Chain Specific prompt | Creativity0.33 | 2 | |
| Idea Generation | Supply Chain | Creativity10 | 2 |