Forecasting on Forecasting benchmark (test)
0CostWW-XGB
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| WW-XGBFamily=No query2026.06 | 0 | 72.5 | 93.3 | 0.094 | 1.538 | |
| BSLI-lowFamily=Ours2026.06 | 0.933 | 92.4 | 96.5 | 0.068 | 1.78 | |
| WW+ED-MLPFamily=Static tool2026.06 | 1 | 96.7 | 97.5 | 0.062 | 1.82 | |
| EDDIFamily=Adaptive FA2026.06 | 1.841 | 77.9 | 95.1 | 0.085 | 1.536 | |
| BSLI-medFamily=Ours2026.06 | 2.179 | 98.3 | 96.6 | 0.068 | 1.867 | |
| ACOFamily=Adaptive FA2026.06 | 2.455 | 88.5 | 97.2 | 0.058 | 1.71 | |
| ED-firstFamily=Fixed workflow2026.06 | 2.5 | 86.2 | 96.5 | 0.073 | 1.64 | |
| SupRouterFamily=Tool router2026.06 | 3.319 | 87.6 | 97 | 0.062 | 1.694 | |
| All-Mod-MLPFamily=Full evidence2026.06 | 4.1 | 93.6 | 97.2 | 0.061 | 1.808 |