# Sakana AI trains a model on its agents' collective research work

> Source: <https://runtimewire.com/article/sakana-ai-mass-agent-teams-self-improvement>
> Published: 2026-10-11 23:04:33+00:00

# Sakana AI trains a model on its agents' collective research work

**Sakana AI's MASS method uses one model to organize research agents, judge their results and learn from selected team runs, with gains on research benchmarks and weaker transfer elsewhere.**

        By [RuntimeWire Staff](https://runtimewire.com/author/runtimewire-staff)
        · Published 

Primary source: [Sakana AI](https://pub.sakana.ai/mass/)

## Why it matters

MASS tests whether agent coordination can become training data for a model's next generation. Its early research gains make the idea concrete, while uneven benchmark transfer and just two cycles leave long-run reliability and real-world costs unresolved.

Sakana AI co-founder and CEO David Ha has made self-evolving AI one of the Tokyo lab's research interests. A new project from [Sakana AI](https://sakana.ai/?ref=runtimewire) and UC Berkeley, described on [Sakana AI's MASS project page](https://pub.sakana.ai/mass/?ref=runtimewire), tests that idea: use a model to organize research agents, let it judge their work, then train the model on the strongest team results.…