---
id: 20261017-T0-11
title: "ARIA：多agent系统的运行时检查与修正"
title_en: "ARIA: Runtime Inspection and Amendment for Multi-Agent Systems"
url: https://ai.daily.yangsir.net/daily/20261017-T0-11
issue_date: 2026-10-17
publish_date: 2026-10-16T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.20780
---

# ARIA：多agent系统的运行时检查与修正

在基于LLM的多agent系统中，一个局部错误会随着其他agent在其基础上继续构建而传播，把本可修正的错误变成任务失败。事后诊断已完成的运行或反复重执行来搜索修正方案，都无法提供及时的干预手段。ARIA提出运行时检查与修正机制，在agent系统执行过程中实时检测并修正错误，防止局部错误扩散为全局失败。该研究以预印本形式发布在arXiv上，针对的是多agent协作中的错误传播核心问题。

## English Version

**ARIA: Runtime Inspection and Amendment for Multi-Agent Systems**

In LLM-based multi-agent systems, a local mistake propagates as other agents build on it, turning a correctable error into a failed task. Diagnosing completed runs or repeatedly re-executing to search for corrections provides no timely intervention. ARIA proposes runtime inspection and amendment, detecting and correcting errors in real time during agent system execution to prevent local errors from cascading into global failures. The work is available as an arXiv preprint, targeting the core problem of error propagation in multi-agent collaboration.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.20780)

**详情页**：https://ai.daily.yangsir.net/daily/20261017-T0-11

---

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