Recursive self-improvement through collective intelligence

Automated excerpt

MASS uses the same model as the executor, optimizer, and evaluator. We compare three generations: the base model \(\mathcal{L}^{(0)}\), the first-round model \(\mathcal{L}^{(1)}\), and the second-round model \(\mathcal{L}^{(2)}\). Win rate of the base model executing each candidate workflow against the same model without a workflow, by search iteration.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.