Feature
Darwin Family: Training-Free Evolutionary Merging Scales LLM Reasoning
Amy Reed · 15 May 2026
Darwin Family introduces a training-free framework for evolutionary merging of large language models via gradient-free weight recombination. It scales frontier-level reasoning by reorganizing encoded latent capabilities.
Researchers introduced Darwin Family, a training-free framework for merging large language models through gradient-free evolutionary recombination in weight space. It applies MRI-Trust weighting to reorganize latent reasoning capabilities already present in the models. This enables scaling of frontier-level reasoning…