ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models

Zhongyuan Wu; Jingyuan Wang; Zexuan Cheng; Yilong Zhou; Weizhi Wang; Juhua Pu; Chao Li; Changqing Ma

AAAI 2026technical0 citations

ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models

Zhongyuan Wu, Jingyuan Wang, Zexuan Cheng, Yilong Zhou, Weizhi Wang, Juhua Pu, Chao Li, Changqing Ma

Abstract

Anomaly detection (AD) is a fundamental task of critical importance across numerous domains. Current systems increasingly operate in rapidly evolving environments that generate diverse yet interconnected data modalities—such as time series, system logs, and tabular records—as exemplified by modern IT systems. Effective AD methods in such environments must therefore possess two critical capabilities: (1) the ability to handle heterogeneous data formats within a unified framework, allowing the model to process and detect multiple modalities in a consistent manner during anomalous events; (2) a strong generalization ability to quickly adapt to new scenarios without extensive retraining. However, most existing methods fall short of these requirements, as they typically focus on single modalities and lack the flexibility to generalize across domains. To address this gap, we introduce a novel paradigm: In-Context Anomaly Detection (ICAD), where anomalies are defined by their dissimilarity to a relevant reference set of normal samples. Under this paradigm, we propose ICAD-LLM, a unified AD framework leveraging Large Language Models

BibTeX

@inproceedings{aaai2026_icadllmoneforall,
  title = {ICAD-LLM: One-for-All Anomaly Detection via In-Context Learning with Large Language Models},
  author = {Zhongyuan Wu and Jingyuan Wang and Zexuan Cheng and Yilong Zhou and Weizhi Wang and Juhua Pu and Chao Li and Changqing Ma},
  booktitle = {AAAI 2026},
  year = {2026}
}