# Evolutionary optimization of model merging recipes

**Source:** https://www.nature.com/articles/s42256-024-00975-8  
**Authors or institution:** Takuya Akiba, Makoto Shing, Yujin Tang, Qi Sun, David Ha  
**Publication date:** 2025-01-28  
**Publication status:** Peer-reviewed article, Nature Machine Intelligence  
**Evidence level:** Demonstrated  
**Date last reviewed in UTC:** 2026-06-26T00:00:00Z

## Direct findings or source content

Automated search can discover high-performing combinations of open-source models and data-flow recipes.

## Cognivirus interpretation

For Cognivirus.com, this source is used to examine risk at the level of adaptive systems, component compositions, evaluator boundaries, and behavioral persistence. The site interpretation is narrower than the source when the source is experimental, and more explicitly qualified when the source is architectural or programmatic.

## Limits

Utility-focused model development; not a system-safety guarantee for adaptive ecologies. That automated model merging preserves safety properties under all derived compositions.

## Source handling

This local file is an original summary and metadata record. It is not a copy of the source paper, report, or website. Copyrighted source material is not reproduced in full.