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:
- System-level latent recursion for MAS
- Lightweight connectors linking heterogeneous agents, plug-and-play across common frameworks
- Inner-outer loop recursive learning for whole-system co-optimization
Code, models, and a tech report are publicly available.
Related event: Stanford's RecursiveMAS Recurses Multi-Agent Systems in Latent Space(2 posts)→
More from Research
- Google Research open-sources PaperOrchestra, a multi-agent framework for writing AI papers — google-research · 2026-11-16
- Kind ICLR Reviewer Raises Score Despite Unresolved Concerns, Citing the Paper's Value — MarkSchmidtUBC · 2026-11-16
- Hand-editing 0.2% of weights plus 100 CPU-minutes turns an English TTS model into an 18MB Sanskrit one — kastnerkyle · 2026-11-16
- Why chirality matters for AI for Science: enantiomers behave differently in biology — madeofAjala · 2026-11-16
- RSS 2027 submissions open with FAQ clarifying two-stage review and negative-result bar — GeorgiaChal · 2026-11-16
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16