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

arXiv: https://arxiv.org/abs/2505.12594 · HTML: https://mlsanity.com/paper/2505.12594/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning](https://mlsanity.com/paper/2305.14909/) (2023)
- [Deep Time Series Models: A Comprehensive Survey and Benchmark](https://mlsanity.com/paper/2407.13278/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [Deep Learning for Medical Anomaly Detection -- A Survey](https://mlsanity.com/paper/2012.02364/) (2020)
- [Large Language Model Agent for Hyper-Parameter Optimization](https://mlsanity.com/paper/2402.01881/) (2024)
- [ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents](https://mlsanity.com/paper/2407.00132/) (2024)
- [PyGOD: A Python Library for Graph Outlier Detection](https://mlsanity.com/paper/2204.12095/) (2022)
- [Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models](https://mlsanity.com/paper/2501.14170/) (2025)
- [PyOD 2: A Python Library for Outlier Detection with LLM-powered Model Selection](https://mlsanity.com/paper/2412.12154/) (2024)
- [MetaOOD: Automatic Selection of OOD Detection Models](https://mlsanity.com/paper/2410.03074/) (2024)
- [Faithful, Unfaithful or Ambiguous? Multi-Agent Debate with Initial Stance for Summary Evaluation](https://mlsanity.com/paper/2502.08514/) (2025)

## Built on by (most cited first, 8 of 8)

- [A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models](https://mlsanity.com/paper/2509.11575/) (2025)
- [A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models](https://mlsanity.com/paper/2509.06609/) (2025)
- [Inside the Unfair Judge: A Mechanistic Interpretability Account of LLM-as-Judge Bias](https://mlsanity.com/paper/2607.11871/) (2026)
- [LLM Agents for Time-Series: A Survey](https://mlsanity.com/paper/2608.26226/) (2026)
- [Integrating Anomaly Detection into Agentic AI for Proactive Risk Management in Human Activity](https://mlsanity.com/paper/2604.19538/) (2026)
- [Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection](https://mlsanity.com/paper/2606.04599/) (2026)
- [Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers](https://mlsanity.com/paper/2607.24419/) (2026)
- [GTA: Graph Theory Agent and Benchmark for Algorithmic Graph Reasoning with LLMs](https://mlsanity.com/paper/2609.12265/) (2026)

## Abstract (arXiv)

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.