arXiv · 2611.20891
From Recursion to Convolution: Parallel Self-Improvement for Multi-Agent Systems
Abstract
Multi-agent self-improvement enables agents to improve through interaction and feedback. However, sequential dependencies across agents and refinement rounds can propagate errors, increase computational costs, and limit parallelism. Moreover, refining individual features or agents in isolation can overlook their dependencies and restrict collective coordination. To address these challenges, we propose ConvRSI, a framework for parallelizing multi-agent self-improvement through convolution. ConvRSI couples intra-agent convolution, which jointly refines related agent features, with inter-agent graph convolution, which aggregates messages according to the collaboration topology. Both stages operate in latent space, enabling parallel updates without repeatedly decoding and re-encoding intermediate messages. Experiments on MATH-500 show that ConvRSI achieves 5.04% performance improvement while reducing 17.27% inference cost, and 45.11% latency compared with RecursiveMAS. It also supports diverse collaboration patterns by representing their topologies as adjacency matrices. These results demonstrate the potential of convolutional co-evolution for efficient multi-agent self-improvement. Our code and datasets are provided in https://github.com/LYA2333/ConvRSI.
Explore related subjects
Keep this discovery
Explore connections, maps & timelines
Zheng Wang, Yuang Liu, Sachith Abeywickrama, Yangkai Ding, Tao Yu, Xinyu Zhang, Hongbo Wang, Qi Ye, Xuefeng Jin, Zhangchun Zhao. 2026-11-16. From Recursion to Convolution: Parallel Self-Improvement for Multi-Agent Systems. https://searcharxiv.com/abs/2611.20891
Citations retain the original authors and DOI and include this site’s record URL. If this discovery service contributed to your research, you can also cite Searcharxiv by Indiciae: BibTeX · RIS.