Sakana AI and UC Berkeley unveil MASS: multi-agent self-supervision for recursive self-improvement
SakanaAILabs · x · 2026-10-13
Sakana AI, in collaboration with UC Berkeley (Somayeh Sojoudi, Matei Zaharia, Donghyun Lee), published MASS (Multi-Agent Self-Supervision), a research direction toward recursive self-improvement (RSI).
- Core idea: at the frontier beyond human knowledge, evaluating discoveries can require scarce expertise or costly experiments, making the model itself the most capable available supervisor. MASS repeatedly optimizes multi-agent workflows, then distills collective intelligence from multi-agent systems as a self-supervision signal.
- Results: improves score per output token over the base model on research benchmarks.
- Paper and code are available; work includes first-author Hyunin Lee (internship at Sakana AI).
Related event: Sakana AI and UC Berkeley Propose MASS for Recursive Self-Improvement(5 posts)→
More from coding & agent
- Sentry founder: complexity is in database and storage, not the language — zeeg · 2026-10-13
- User says Grok Bot researched and booked his entire Lisbon trip with one prompt — elonmusk · 2026-10-13
- GitHub Actions tip: always cache dependencies — pipelines cut from 20 min to 3 min — vboykis · 2026-10-13
- Grok Bot turns X bookmarks into a Notion second brain in this automated workflow — elonmusk · 2026-10-13
- Open-source Android app runs Codex CLI on your phone via proot, no root needed — 3amae404 · 2026-10-13
- User says Grok replaced his ChatGPT, Claude and Cursor workflows entirely — elonmusk · 2026-10-13