Simulation deck generation on GEOS v1 (val)
92.1TreeSimX+M
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| X+MRetrieval=false, Refine loop=false, Validator=true, Memory=true2026.06 | 92.1 | 0.011 | |
| S+MRetrieval=false, Refine loop=true, Validator=false, Memory=true2026.06 | 91.9 | 0.009 | |
| Self-EvolveRetrieval=false, Refine loop=true, Validator=true, Memory=true2026.06 | 91.9 | 0.009 | |
| S+XRetrieval=false, Refine loop=true, Validator=true, Memory=false2026.06 | 91.7 | 0.007 | |
| S+X+MRetrieval=false, Refine loop=true, Validator=true, Memory=true2026.06 | 91.1 | 0.001 | |
| VanillaRetrieval=false, Refine loop=false, Validator=false, Memory=false2026.06 | 91 | — | |
| Self-Evolve-proseRetrieval=false, Refine loop=true, Validator=true, Memory=true2026.06 | 89.7 | 0.013 | |
| R+XRetrieval=true, Refine loop=false, Validator=true, Memory=false2026.06 | 89.3 | 0.017 | |
| R+MRetrieval=true, Refine loop=false, Validator=false, Memory=true2026.06 | 88.5 | 0.025 | |
| R+S+X+MRetrieval=true, Refine loop=true, Validator=true, Memory=true2026.06 | 88.5 | 0.025 | |
| R+SRetrieval=true, Refine loop=true, Validator=false, Memory=false2026.06 | 85.7 | 0.053 |