Recursive Multi-Agent Systems

Recursive Multi-Agent Systems

From Daily Paper Cast by Jingwen Liang, Gengyu Wang

April 30, 2026 · 25 min · Episode 1819

About this episode

This episode discusses Recursive Multi-Agent Systems and their potential for enhancing agent collaboration through recursion.

🤗 Upvotes: 131 | cs.AI, cs.CL, cs.LG Authors: Xiyuan Yang, Jiaru Zou, Rui Pan, Ruizhong Qiu, Pan Lu, Shizhe Diao, Jindong Jiang, Hanghang Tong, Tong Zhang, Markus J. Buehler, Jingrui He, James Zou Title: Recursive Multi-Agent Systems Arxiv: http://arxiv.org/abs/2604.25917v1 Abstract: Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We extend such scaling principle from a single model to multi-agent systems, and ask: Can agent collaboration itself be scaled through recursion? To this end, we introduce RecursiveMAS, a recursive multi-agent framework that casts the entire system as a unified latent-space recursive computation. RecursiveMAS connects heterogeneous agents as a collaboration loop through the lightweight RecursiveLink module, enabling in-distribution latent thoughts generation and cross-agent latent state transfer. To optimize our framework, we develop an inner-outer loop learning algorithm for iterative whole-system co-optimization through shared gradient-based credit assignment across recursion rounds. Theoretical analyses of runtime complexity and…

People in this episode

Hosts: Jingwen Liang, Gengyu Wang

Topics covered

  • multi-agent systems
  • recursive models
  • collaboration
  • machine learning
  • AI

Keywords

  • RecursiveMAS
  • agent collaboration
  • latent states
  • learning algorithm
  • runtime complexity

More episodes of Daily Paper Cast

Explore listener stats, chart rankings, contacts and more on the Daily Paper Cast podcast page.