**摘要**
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 m
👤 作者: Zhen Yang, Xiaogang Xu, 王文 , Cong Chen, Xander Xu, Ying-Cong Chen

---
🔗 **[多Agent推理中的流媒体沟通](https://arxiv.org/abs/2606.05158v1)**

> Streaming Communication in Multi-Agent Reasoning
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-04 14:00