---
id: 20260821-T0-04
title: "多智能体系统可靠性下降，根因在于并发控制缺失"
title_en: "Multi-Agent Systems Fail Due to Lack of Concurrency Control, Paper Argues"
url: https://ai.daily.yangsir.net/daily/20260821-T0-04
issue_date: 2026-08-21
publish_date: 2026-08-20T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2608.18092
---

# 多智能体系统可靠性下降，根因在于并发控制缺失

一篇新发表于arXiv的立场论文指出，LLM-based多智能体系统在增加智能体数量时，可靠性不升反降，其根本原因并非协作策略问题，而是并发控制缺失。论文认为，多个智能体同时读写共享状态，导致数据竞争和一致性问题。作者主张应将数据库领域的并发控制机制引入MAS设计，以提升系统稳定性。这一观点为多智能体系统开发提供了新的诊断思路。

## English Version

**Multi-Agent Systems Fail Due to Lack of Concurrency Control, Paper Argues**

A new position paper on arXiv argues that reliability in LLM-based multi-agent systems drops as agents are added, not due to poor coordination but fundamentally due to missing concurrency control. When agents concurrently read and write shared state, data races and inconsistency occur. The authors advocate borrowing concurrency control mechanisms from database systems to improve MAS stability, offering a fresh diagnostic lens for developers building multi-agent applications.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2608.18092)

**详情页**：https://ai.daily.yangsir.net/daily/20260821-T0-04

---

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