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

TL;DR

AnomaMind introduces an agentic, tool-augmented framework for time series anomaly detection that iteratively localizes, diagnoses, and refines anomalies through a structured, reasoning-aware process, outperforming traditional methods.

Contribution

It presents a novel anomaly detection approach reformulating the task as a sequential decision-making process with tool interactions and self-reflection, enabling adaptive and context-aware detection.

Findings

Consistently improves detection performance across diverse settings.

Utilizes reinforcement learning for task-specific optimization.

Supports multi-turn tool interactions for diagnostic analysis.

Abstract

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 inputs, rather than an evidence-driven diagnostic process. As a result, they often struggle when anomalies exhibit strong context dependence or diverse patterns. We argue that these limitations stem from the lack of adaptive feature preparation, reasoning-aware detection, and iterative refinement during inference. 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 structured workflow that progressively localizes anomalous intervals in a coarse-to-fine manner, augments detection through multi-turn tool interactions for adaptive feature preparation, and refines anomaly decisions via self-reflection. The workflow is supported by a set of reusable tool engines, enabling context-aware diagnostic analysis. A key design of AnomaMind is an explicitly designed hybrid inference mechanism for tool-augmented anomaly detection. In this mechanism, general-purpose models are responsible for autonomous tool interaction and self-reflective refinement, while core anomaly detection decisions are learned through reinforcement learning under verifiable workflow-level feedback, enabling task-specific optimization within a flexible reasoning framework. Extensive experiments across diverse settings demonstrate that AnomaMind consistently improves anomaly detection performance. The code is available at https://anonymous.4open.science/r/AnomaMind.