---
id: 20260607-T0-03
title: "智能体间行动-状态通信提升多系统效率"
title_en: "Action-state communication boosts multi-agent efficiency"
url: https://ai.daily.yangsir.net/daily/20260607-T0-03
issue_date: 2026-06-07
publish_date: 2026-06-06T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2606.05304
---

# 智能体间行动-状态通信提升多系统效率

arXiv 论文《智能体应如何沟通？》提出，传统多智能体系统通过角色分工和固定轮转传递自然语言，效率低下。新方案引入行动-状态通信框架，约束传递内容结构化信息，使智能体能更高效地协作完成复杂任务，减少语义误解。

## English Version

**Action-state communication boosts multi-agent efficiency**

arXiv paper 'What Should Agents Say?' argues traditional multi-agent systems' unconstrained natural language communication is inefficient. It proposes an action-state communication framework to structure agent interactions, enabling more efficient collaboration and reducing semantic misunderstandings.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2606.05304)

**详情页**：https://ai.daily.yangsir.net/daily/20260607-T0-03

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*