AI Radar
Support
LiveUpdated 2026-11-06 15:57 UTC

RecursiveMAS

RecursiveMAS — 💻 Project & Demo

RecursiveMAS is 💻 Project & Demo. It is ranked #8003 on the AI Radar, in AI agents, first seen 37 days ago and shared in 1 post (730 views).

Visit recursivemas.github.io

What RecursiveMAS says about itself

Scaling agent collaboration through recurrent depth in latent space. +8.3% accuracy, up to 2.4x speedup, up to 75.6% fewer tokens across 9 benchmarks.

RecursiveMAS Looped Multi-Agent Framework Recursive Multi-Agent Systems Scaling Agent Collaboration through Recurrent Depth in Latent Space NeurIPS 2026 Jiaru Zou 1,† , Rui Pan 2 , Ruizhong Qiu 2 , Pan Lu 1 , Shizhe Diao 3 , Jindong Jiang 3 , Hanghang Tong 2 , Tong Zhang 2 , Markus J. Buehler 4 , Jingrui He 2,✉ , James Zou 1,✉ 1 Stanford University · 2 University of Illinois Urbana-Champaign · 3 NVIDIA · 4 MIT † Project Lead · ✉ Corresponding Authors 🤗 Paper Code Demo arXiv YouTube 🤗 Models 🤗 Data VB VentureBeat Post Contact Cite +8.3% Avg. Accuracy Gain Across All Benchmarks 2.4× End-to-End Speedup Compared to…

Alternatives to RecursiveMAS

RecursiveMAS in numbers

FAQ

What is RecursiveMAS?

💻 Project & Demo It was first shared on X 37 days ago and is ranked #8003 on the AI Radar.

Is RecursiveMAS free?

Pricing is not stated on the page we read.

Who shared RecursiveMAS?

1 account on X, including @zainhas, in 1 post totalling 730 views.

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:57 UTC. Full method.