RecursiveMAS casts multi-agent systems as latent-space recursion, unlocking a new scaling axis

james_y_zou · x · 2026-09-30

Jiaru Zou and collaborators released RecursiveMAS, a learning framework asking whether agent collaboration itself can be scaled through recursion. It models the entire multi-agent system as a unified latent-space recursion, opening a scaling axis beyond bigger models or more agents.

Key features:

Code, models, and a tech report are publicly available.

Related event: Stanford's RecursiveMAS Recurses Multi-Agent Systems in Latent Space(2 posts)→

Original post →

More from Research

Research channel →