# What Sakana's evolutionary model merging demonstrated

> M2N2 searches for useful combinations of model parameters; biological language describes the search method.

Source: https://fullbytedeveloper.com/blog/sakana-natural-niches-model-merging
Originally posted: 2025-09-21
Published here: 2026-11-06

Sakana AI's August 2025 research described M2N2, or Model Merging of Natural Niches. The method searches for combinations of existing model parameters using ideas inspired by evolution. The social post's reference to models having offspring is a metaphor for producing merged models. [1]

## What changes during the search

M2N2 varies the boundaries used to divide models before merging. It encourages different models to specialize and uses their complementary strengths to choose combinations worth evaluating. Those choices reduce reliance on manually fixed merging boundaries. [1]

## What the experiments showed

The research included image classification, a combination of mathematics and agent-task specialists, and text-to-image models. Sakana reported gains on the evaluated tasks, including retaining English capability while improving Japanese image prompts. [1]

The results do not mean every merged model will outperform its inputs on every task. Check the paper's evaluation sets and compare the merged model with each starting model on your own requirements. Include capabilities that should remain intact, because improving one score can hide a regression elsewhere.

## Sources

1. [Sakana M2N2 research summary](https://sakana.ai/m2n2/)

## Original posts

- [Instagram post](https://www.instagram.com/fullbytedeveloper/p/DO2hbAZDKMt/)