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

2026-02-14

AI Summary

This work addresses the limitations of existing time series anomaly detection methods, which struggle with strong contextual dependencies and diverse anomaly patterns due to their reliance on fixed feature inputs. To overcome this, we propose the first agent-based, tool-augmented reasoning framework that reformulates anomaly detection as a sequential decision-making process. The agent employs a coarse-to-fine strategy to localize anomalies, adaptively constructs features through multi-round interactions with external tools, and iteratively refines its predictions via a self-reflection mechanism. By integrating the tool-calling and reflective capabilities of general-purpose models with a reinforcement learning–driven core detection policy, our framework enables task-specific optimization under verifiable workflow feedback. Experiments demonstrate that the proposed approach significantly improves both localization accuracy and decision reliability across a range of complex scenarios.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Reasoning under Uncertainty: Sequential Decision Making
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• time series anomaly detection
• context dependence
• anomaly patterns
• evidence-driven diagnosis
• adaptive feature preparation

Innovation

• agentic anomaly detection
• tool-augmented reasoning
• adaptive feature preparation
• self-reflective refinement
• reinforcement learning