Abstract
The present disclosure relates to an advanced anomaly detection system for high-volume log data that incorporates a dual-agent architecture consisting of a Detector Agent and an Evaluator Agent. The Detector Agent is configured to identify anomalies using hybrid quantum-classical processing techniques, including quantum-enhanced machine learning methods such as a Hamiltonian Quantum Generative Autoencoder and advanced transformer models. The Evaluator Agent critiques the outputs from the Detector Agent, providing continuous feedback for iterative improvement. This feedback loop allows for dynamic adjustments to enhance detection accuracy. Additionally, the system integrates with Splunk for real-time log data ingestion and employs a Large Language Model to generate explanations for the detected anomalies. Overall, the framework aims to improve anomaly detection capabilities while mitigating false positives, leveraging both quantum and classical approaches.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Guo, Fuming, "ANOMALY DETECTION AGENT EMPOWERED BY QUANTUM AI AND MACHINE LEARNING", Technical Disclosure Commons, (September 02, 2025)
https://www.tdcommons.org/dpubs_series/8540