List your company

Simulation deck generation on GEOS v1 (held-out-eval)

78.9TreeSim ScoreSelf-Evolve
71.72473.58775.4577.313Jun 8, 2026

Evaluation results

MethodLinks
Self-EvolveRetrieval=false, Refine loop=true, Validator=true, Memory=true2026.0678.90.069
S+X+MRetrieval=false, Refine loop=true, Validator=true, Memory=true2026.0678.30.063
S+XRetrieval=false, Refine loop=true, Validator=true, Memory=false2026.0678.10.061
Self-Evolve-proseRetrieval=false, Refine loop=true, Validator=true, Memory=true2026.0677.50.055
X+MRetrieval=false, Refine loop=false, Validator=true, Memory=true2026.0676.80.048
VanillaRetrieval=false, Refine loop=false, Validator=false, Memory=false2026.0672—