Autoregressive Multimodal Anomaly Detection with Large Language Models for Microservice Systems

查看原文 / View Original 编辑 / Edit

Computer Science > Machine Learning arXiv:2610.31722 (cs) [Submitted on 22 Oct 2026] Title: Autoregressive Multimodal Anomaly Detection with Large Language Models for Microservice Systems Authors: Yixiang Tang, Fagui Liu, Guoxiang Zhong, Xi Yao, C.L. Philip Chen.

计算机科学 > 机器学习 arXiv:2610.31722 (cs) [提交于 2026 年 10 月 22 日] 标题：基于大语言模型的微服务系统自回归多模态异常检测作者：Yixiang Tang, Fagui Liu, Guoxiang Zhong, Xi Yao, C.L. Philip Chen。

Abstract: Microservice systems have become a dominant architecture for large-scale cloud applications, enabling rapid deployment and elastic scaling. However, ensuring the reliability and availability of microservice systems critically relies on effective anomaly detection, as failures and performance anomalies can quickly propagate across services and severely impact end-to-end system behavior.

摘要：微服务系统已成为大规模云应用的主流架构，支持快速部署和弹性扩展。然而，确保微服务系统的可靠性和可用性关键在于有效的异常检测，因为故障和性能异常会迅速在服务间传播，并严重影响端到端的系统行为。

Existing multimodal anomaly detection approaches for microservice systems often struggle with two fundamental limitations: (i) the neglect of modality-specific characteristics in favor of cross-modality fusion, and (ii) the “identity-shortcut” problem that affects the feature reconstruction process.

现有的微服务系统多模态异常检测方法通常面临两个根本性局限：(i) 为了跨模态融合而忽视了模态特定的特征，以及 (ii) 影响特征重构过程的“身份捷径”问题。

To address these issues, we propose LLMMAD, an autoregressive multimodal anomaly detection framework for microservice systems based on Large Language Models (LLMs). Initially, to reconcile cross-modality fusion with modality-specific preservation, LLMMAD embeds and recombines multimodal data into a unified sequence for LLM processing to model inter-modality relationships, while employing modality-wise reconstruction heads to retain modality-specific information.

为了解决这些问题，我们提出了 LLMMAD，这是一个基于大语言模型（LLM）的微服务系统自回归多模态异常检测框架。首先，为了协调跨模态融合与模态特定信息的保留，LLMMAD 将多模态数据嵌入并重组为统一序列供 LLM 处理，以建模模态间的关系，同时采用模态特定的重构头来保留模态特有的信息。

Subsequently, to eliminate the identity-shortcut, we implement a prediction-driven autoregressive objective, under which the model predicts future states rather than copies current inputs. Finally, we conduct extensive experiments on three real-world datasets. The results demonstrate that LLMMAD consistently outperforms state-of-the-art methods, achieving F1-score improvements of 3.1%, 1.4%, and 0.9%, respectively, thereby providing a more reliable solution for microservice monitoring.

随后，为了消除“身份捷径”，我们实现了一种预测驱动的自回归目标，在该目标下，模型预测未来状态而非复制当前输入。最后，我们在三个真实世界数据集上进行了广泛的实验。结果表明，LLMMAD 在性能上持续优于现有最先进的方法，F1 分数分别提升了 3.1%、1.4% 和 0.9%，从而为微服务监控提供了一种更可靠的解决方案。