AD-AGENT: A Multi-agent Framework for End-to-end Anomaly Detection

TL;DR

AD-AGENT is an LLM-driven multi-agent framework that automates the creation of anomaly detection pipelines from natural language instructions, simplifying complex library integration for non-experts.

Contribution

It introduces a novel multi-agent system that converts natural language into executable anomaly detection workflows, integrating multiple libraries and enabling iterative debugging.

Findings

Produces reliable AD scripts across libraries

Recommends competitive anomaly detection models

Facilitates non-experts in building AD pipelines

Abstract

Anomaly detection (AD) is essential in areas such as fraud detection, network monitoring, and scientific research. However, the diversity of data modalities and the increasing number of specialized AD libraries pose challenges for non-expert users who lack in-depth library-specific knowledge and advanced programming skills. To tackle this, we present AD-AGENT, an LLM-driven multi-agent framework that turns natural-language instructions into fully executable AD pipelines. AD-AGENT coordinates specialized agents for intent parsing, data preparation, library and model selection, documentation mining, and iterative code generation and debugging. Using a shared short-term workspace and a long-term cache, the agents integrate popular AD libraries like PyOD, PyGOD, and TSLib into a unified workflow. Experiments demonstrate that AD-AGENT produces reliable scripts and recommends competitive models across libraries. The system is open-sourced to support further research and practical applications in AD.