Constraint Satisfaction and Optimization
Open access
Abstract
Abstract
Multi-agent reasoning systems adopt a "generate-then-transfer" paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce StreamMA, a multi-agent reasoning system that streams each reasoning step to downstream agents as soon as it is generated, pipelining adjacent agents and thus reducing latency. Surprisingly, this pipelining also improves effectiveness: because multi-step reasoning quality is non-uniform and early steps are more reliable than later ones, working with these reliable early steps instead of the full chain prevents error-prone late steps from misleading downstream agents. We formalize both advantages with the first closed-form joint analysis of stream, serial, and single protocols, deriving the effectiveness ordering, speedup upper bound, and cost ratio. Across eight reasoning benchmarks spanning mathematics, science, and code, two frontier LLMs (Claude Opus 4.6 and GPT-5.4), and three topologies (Chain, Tree, Graph), StreamMA outperforms both baselines (avg. +7.3 pp, max +22.4 pp on HMMT 2026; Claude Opus 4.6-high). Beyond these contributions, we discover a "step-level scaling law": increasing per-agent steps consistently improves both effectiveness and efficiency, a new scaling dimension orthogonal to and composable with agent-count scaling.
Direct answer
What can I do from this paper page?
Use this page to scan "Streaming Communication in Multi-Agent Reasoning" quickly: start with the summary and abstract, then check the authors, source, topics, and related papers. From here, open Scollr to follow Constraint Satisfaction and Optimization research, save the paper, or map adjacent work.
Research areas
Follow related topics
Citation
BibTeX
@article{Yang2026Streaming,
title = {Streaming Communication in Multi-Agent Reasoning},
author = {Zhen Yang and Xiaogang Xu and Wen Wang and Cong Chen and Xander Xu and Ying-Cong Chen},
journal = {arXiv (Cornell University)},
year = {2026},
url = {https://arxiv.org/abs/2606.05158}
}FAQ
Using this paper in a discovery workflow
How do I find related work for this paper?
Use the related papers and topic links on this page as starting points. In Scollr, you can also open the paper and build a literature map around its references, citing papers, and related work.
How can I keep up with new Constraint Satisfaction and Optimization research papers?
Follow Constraint Satisfaction and Optimization research in Scollr. New papers from the topic flow into a personalized feed, and you can save useful studies to revisit later.
Can I cite this paper from this page?
This page includes a static BibTeX block for Streaming Communication in Multi-Agent Reasoning. Always verify the DOI, source, and publication details against the publisher record before submitting a manuscript.
Follow this research in Scollr
Follow the topics and authors behind this paper, save useful studies, and build a literature map when you are ready to go deeper.
Get the app