← Tuesday, October 13, 2026AgentsPaper

MASS optimizes multi-agent workflows through self-supervision

pub.sakana.ai 18 min read Editor score 8/10

MASS repeatedly optimizes multi-agent workflows and distills their collective output into a self-supervision signal; the authors report improved score per output token over a base model on research benchmarks and provide code. The method and evidence make it relevant to teams building agent systems and evaluating their efficiency.

What: MASS repeatedly optimizes multi-agent workflows and distills collective intelligence into self-supervision for recursive self-improvement.
Method: It frames the model being improved as its own optimizer and evaluator when stronger teachers or reliable human feedback may be unavailable.
Why it matters: MASS improves score per output token over the base model on research benchmarks.

MASS turns multi-agent work into collective intelligence used as a self-supervision signal. Sketched from the article's own text.

Read on pub.sakana.ai → Hacker News · 79 comments

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.