# ADT: Agent-based Dynamic Thresholding for Anomaly Detection

arXiv: https://arxiv.org/abs/2312.01488 · HTML: https://mlsanity.com/paper/2312.01488/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 31 references that are in the map.
- First posted on arXiv 3 Dec 2023.

## Builds on (most cited first, 3 of 3)

- [Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding](https://mlsanity.com/paper/1802.04431/) (2018)
- [Deep Learning for Anomaly Detection: A Survey](https://mlsanity.com/paper/1901.03407/) (2019)
- [Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications](https://mlsanity.com/paper/1802.03903/) (2018)

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

- [Who's the Mole? Modeling and Detecting Intention-Hiding Malicious Agents in LLM-Based Multi-Agent Systems](https://mlsanity.com/paper/2507.04724/) (2025)
- [A Meta-Learning Approach for Multi-Objective Reinforcement Learning in Sustainable Home Environments](https://mlsanity.com/paper/2407.11489/) (2024)
- [Segmented Confidence Sequences and Multi-Scale Adaptive Confidence Segments for Anomaly Detection in Nonstationary Time Series](https://mlsanity.com/paper/2508.06638/) (2025)
- [ARES: Anomaly Recognition Model For Edge Streams](https://mlsanity.com/paper/2511.22078/) (2025)
- [Integrating Anomaly Detection into Agentic AI for Proactive Risk Management in Human Activity](https://mlsanity.com/paper/2604.19538/) (2026)

## Abstract (arXiv)

The complexity and scale of IT systems are increasing dramatically, posing many challenges to real-world anomaly detection. Deep learning anomaly detection has emerged, aiming at feature learning and anomaly scoring, which has gained tremendous success. However, little work has been done on the thresholding problem despite it being a critical factor for the effectiveness of anomaly detection. In this paper, we model thresholding in anomaly detection as a Markov Decision Process and propose an agent-based dynamic thresholding (ADT) framework based on a deep Q-network. The proposed method can be integrated into many systems that require dynamic thresholding. An auto-encoder is utilized in this study to obtain feature representations and produce anomaly scores for complex input data. ADT can adjust thresholds adaptively by utilizing the anomaly scores from the auto-encoder and significantly improve anomaly detection performance. The properties of ADT are studied through experiments on three real-world datasets and compared with benchmarks, hence demonstrating its thresholding capability, data-efficient learning, stability, and robustness. Our study validates the effectiveness of reinforcement learning in optimal thresholding control in anomaly detection.