跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2611.10612 · v1

An Agentic Multi-Agent Framework for System Log Anomaly Detection

首次提交 2026-11-07 17:30
版本更新 2026-11-07 17:30
雷达观测 2026-11-10 11:14
arXiv ↗PDF ↗

摘要

As enterprise systems grow in scale and complexity, manual log analysis and conventional SIEM tools struggle to keep pace with the volume and diversity of incidents. To address this challenge, this paper proposed a multi-agent AI framework supporting in analyzing the system log to trace the attack forensic in the system more effectively and efficiently. The framework is designed using n8n platform and Gemini large language model. The framework consists of 7 AI agent layers. Each agent work on a specific task. When the task is done, the agent will forward the result to the output-associated agent of the next layer. The multi agent model improves the analysis velocity, so it is able to support numerous log analysis requirement at the same time. We deployed 16 test cases to test operation of the multi agent workflow, and evaluate the accuracy per test case and the operative performance. The result findings are very promising.

作者备注:14th International Conference on Multidisciplinary Research (ICMR 2026), ISBN 978-974-474-120-2, Thaksin University Publisher, Bangkok, Thailand, pp. 63-80, 2026 (Published)

AI 论文解读

基于摘要 · 非全文审阅

此版本尚未生成 AI 解读。解读由后台任务生成并按论文版本保存,登录后共享已有结果。

版本差异

目前只收录了一个版本。收录下一版后,可以对照标题、作者、分类和摘要。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v1 · 2026-11-07 17:30 · 最新观测版本

An Agentic Multi-Agent Framework for System Log Anomaly Detection

As enterprise systems grow in scale and complexity, manual log analysis and conventional SIEM tools struggle to keep pace with the volume and diversity of incidents. To address this challenge, this paper proposed a multi-agent AI framework supporting in analyzing the system log to trace the attack forensic in the system more effectively and efficiently. The framework is designed using n8n platform and Gemini large language model. The framework consists of 7 AI agent layers. Each agent work on a specific task. When the task is done, the agent will forward the result to the output-associated agent of the next layer. The multi agent model improves the analysis velocity, so it is able to support numerous log analysis requirement at the same time. We deployed 16 test cases to test operation of the multi agent workflow, and evaluate the accuracy per test case and the operative performance. The result findings are very promising.

查看此版本解读 →查看此版本原文 ↗