Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Gu, Yile, Xiong, Yifan, Mace, Jonathan, Jiang, Yuting, Hu, Yigong, Kasikci, Baris, Cheng, Peng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916581650464768
author Gu, Yile
Xiong, Yifan
Mace, Jonathan
Jiang, Yuting
Hu, Yigong
Kasikci, Baris
Cheng, Peng
author_facet Gu, Yile
Xiong, Yifan
Mace, Jonathan
Jiang, Yuting
Hu, Yigong
Kasikci, Baris
Cheng, Peng
contents Observability in cloud infrastructure is critical for service providers, driving the widespread adoption of anomaly detection systems for monitoring metrics. However, existing systems often struggle to simultaneously achieve explainability, reproducibility, and autonomy, which are three indispensable properties for production use. We introduce Argos, an agentic system for detecting time-series anomalies in cloud infrastructure by leveraging large language models (LLMs). Argos proposes to use explainable and reproducible anomaly rules as intermediate representation and employs LLMs to autonomously generate such rules. The system will efficiently train error-free and accuracy-guaranteed anomaly rules through multiple collaborative agents and deploy the trained rules for low-cost online anomaly detection. Through evaluation results, we demonstrate that Argos outperforms state-of-the-art methods, increasing $F_1$ scores by up to $9.5\%$ and $28.3\%$ on public anomaly detection datasets and an internal dataset collected from Microsoft, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2501_14170
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models
Gu, Yile
Xiong, Yifan
Mace, Jonathan
Jiang, Yuting
Hu, Yigong
Kasikci, Baris
Cheng, Peng
Machine Learning
Distributed, Parallel, and Cluster Computing
Multiagent Systems
Observability in cloud infrastructure is critical for service providers, driving the widespread adoption of anomaly detection systems for monitoring metrics. However, existing systems often struggle to simultaneously achieve explainability, reproducibility, and autonomy, which are three indispensable properties for production use. We introduce Argos, an agentic system for detecting time-series anomalies in cloud infrastructure by leveraging large language models (LLMs). Argos proposes to use explainable and reproducible anomaly rules as intermediate representation and employs LLMs to autonomously generate such rules. The system will efficiently train error-free and accuracy-guaranteed anomaly rules through multiple collaborative agents and deploy the trained rules for low-cost online anomaly detection. Through evaluation results, we demonstrate that Argos outperforms state-of-the-art methods, increasing $F_1$ scores by up to $9.5\%$ and $28.3\%$ on public anomaly detection datasets and an internal dataset collected from Microsoft, respectively.
title Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Multiagent Systems
url https://arxiv.org/abs/2501.14170