# AnomaMind: Agentic Time Series Anomaly Detection with Tool-Augmented Reasoning

arXiv: https://arxiv.org/abs/2602.13807 · HTML: https://mlsanity.com/paper/2602.13807/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 57 references that are in the map.
- First posted on arXiv 14 Feb 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 30)

- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [One Fits All:Power General Time Series Analysis by Pretrained LM](https://mlsanity.com/paper/2302.11939/) (2023)
- [Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy](https://mlsanity.com/paper/2110.02642/) (2021)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)
- [TranAD: Deep Transformer Networks for Anomaly Detection in Multivariate Time Series Data](https://mlsanity.com/paper/2201.07284/) (2022)
- [AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models](https://mlsanity.com/paper/2308.15366/) (2023)
- [Time-Series Anomaly Detection Service at Microsoft](https://mlsanity.com/paper/1906.03821/) (2019)
- [Deep Learning for Time Series Anomaly Detection: A Survey](https://mlsanity.com/paper/2211.05244/) (2022)
- [Empowering Time Series Analysis with Large Language Models: A Survey](https://mlsanity.com/paper/2402.03182/) (2024)
- [TAB: Unified Benchmarking of Time Series Anomaly Detection Methods](https://mlsanity.com/paper/2506.18046/) (2025)
- [TODS: An Automated Time Series Outlier Detection System](https://mlsanity.com/paper/2009.09822/) (2020)
- [Can LLMs Understand Time Series Anomalies?](https://mlsanity.com/paper/2410.05440/) (2024)
- [Large language models can be zero-shot anomaly detectors for time series?](https://mlsanity.com/paper/2405.14755/) (2024)
- [Large Language Models can Deliver Accurate and Interpretable Time Series Anomaly Detection](https://mlsanity.com/paper/2405.15370/) (2024)
- [Agent-R1: A Unified and Modular Framework for Agentic Reinforcement Learning](https://mlsanity.com/paper/2511.14460/) (2025)
- [Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection](https://mlsanity.com/paper/2401.15123/) (2024)
- [TimeART: Towards Agentic Time Series Reasoning via Tool-Augmentation](https://mlsanity.com/paper/2601.13653/) (2026)
- [Can LLMs Serve As Time Series Anomaly Detectors?](https://mlsanity.com/paper/2408.03475/) (2024)
- [TableMind: An Autonomous Programmatic Agent for Tool-Augmented Table Reasoning](https://mlsanity.com/paper/2509.06278/) (2025)
- [Argos: Agentic Time-Series Anomaly Detection with Autonomous Rule Generation via Large Language Models](https://mlsanity.com/paper/2501.14170/) (2025)
- [When Model Meets New Normals: Test-time Adaptation for Unsupervised Time-series Anomaly Detection](https://mlsanity.com/paper/2312.11976/) (2023)
- [AlphaCast: A Human Wisdom-LLM Intelligence Co-Reasoning Framework for Interactive Time Series Forecasting](https://mlsanity.com/paper/2511.08947/) (2025)
- [Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecasting](https://mlsanity.com/paper/2602.01776/) (2026)
- [MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoning](https://mlsanity.com/paper/2602.03164/) (2026)
- [xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection](https://mlsanity.com/paper/2506.22837/) (2025)
- [Refining Time Series Anomaly Detectors using Large Language Models](https://mlsanity.com/paper/2503.21833/) (2025)
- [Extracting Actionable Insights from Building Energy Data using Vision LLMs on Wavelet and 3D Recurrence Representations](https://mlsanity.com/paper/2509.21934/) (2025)
- [Evaluating Large Language Models for Time Series Anomaly Detection in Aerospace Software](https://mlsanity.com/paper/2601.12448/) (2026)

## Built on by (most cited first, 5 of 5)

- [CastFlow: Learning Role-Specialized Agentic Workflows for Time Series Forecasting](https://mlsanity.com/paper/2604.27840/) (2026)
- [Failures Reveal What Metrics Miss: An Evidence-Driven Agent for Recursive Refinement of ECG Classifiers](https://mlsanity.com/paper/2607.24419/) (2026)
- [Memory in Deep Time-Series Models](https://mlsanity.com/paper/2609.06006/) (2026)
- [When Tomorrow Becomes Today: Self-Evolving Policies for Agentic Time-Series Forecasting](https://mlsanity.com/paper/2609.24862/) (2026)
- [READ-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosis](https://mlsanity.com/paper/2609.32123/) (2026)

## Abstract (arXiv)

Time series anomaly detection is critical in many real-world applications, where effective solutions must localize anomalous regions and support reliable decision-making under complex settings. However, most existing methods frame anomaly detection as a purely discriminative prediction task with fixed feature representations, rather than an evidence-driven diagnostic process. As a result, they often struggle when anomalies exhibit strong context dependence, diverse patterns, or domain shifts across datasets. To address these challenges, we propose AnomaMind, an agentic time series anomaly detection framework that reformulates anomaly detection as a sequential decision-making process. AnomaMind operates through a coarse-to-fine workflow that first localizes suspicious intervals, then constructs diagnostic evidence through tool interaction, and finally refines anomaly decisions through self-reflection. The workflow is supported by a toolkit box that combines knowledge memory and numerical diagnostics: visual anomaly patterns mined from training data and domain knowledge provide contextual guidance, while statistical, value-based, change-based, and region-level operators provide measurable evidence for verification. AnomaMind further adopts a hybrid inference mechanism in which general-purpose models handle flexible reasoning, tool invocation, and refinement, while a detection-specific policy is optimized with rule-based rewards for parsable outputs, F1-score alignment, and false-positive control. Extensive experiments under both in-domain and cross-domain settings demonstrate that AnomaMind consistently improves anomaly detection performance and enhances generalization across heterogeneous anomaly patterns, validating the effectiveness of tool-augmented reasoning for anomaly detection. The code is available at https://github.com/Xiaoyu-Tao/AnomaMind-TS.