# Sakana AI Tests Agent Team Research for Self-Improvement

> Sakana AI uses agents' research to train a model that self-improves.
- Title: Sakana AI Tests Agent Team Research for Self-Improvement
- Summary: Sakana AI uses agents' research to train a model that self-improves. Sakana AI tests if agent teams' collective research can train a model for…
- Keywords: sakana ai, mass, uc berkeley, self-improvement, ai model, agent teams, technology, Sakana, Tests, Agent, Team, Research
- Source: RuntimeWire — https://runtimewire.com/article/sakana-ai-mass-agent-teams-self-improvement
- Author: RuntimeWire
- Published: 2026-10-11T23:04:33.117+00:00
- Read time: 1 min
- Topics: sakana ai, mass, uc berkeley, self-improvement, ai model, agent teams, technology, ai
## Sakana AI
Sakana AI co-founder and CEO David Ha has made self-evolving AI one of the Tokyo lab's research interests.
## MASS Project
A new project from Sakana AI and UC Berkeley tests using a model to organize research agents and train on strongest team results.
## Early Results
MASS tests whether agent coordination can become training data for a model's next generation with early research gains but unresolved long-term reliability and costs.
## Key takeaway

Sakana AI tests if agent teams' collective research can train a model for self-improvement.