AEGIS: Toward Expert-in-the-loop Industrial Anomaly Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41619-41621
DOI: 10.1609/aaai.v40i48.42359 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Dongmin Kim und 6 weiteren Autor:innen.
Abstract (Originalsprache)
Anomaly detection platforms in real-world environments require continuous interaction between automated systems and domain experts, as anomalies evolve dynamically and their definitions vary across contexts. Therefore, an effective platform must collaborate with experts and incorporate their feedback to update the system. This paper introduces AEGIS, an anomaly detection platform that aims to support interaction between domain experts and data-driven agents through three core capabilities: (1) data-driven insights through real-time monitoring, explanations, and distribution shift detection, which invoke customized tools to generate appropriate responses, (2) an expert feedback interface for labeling and direct updates via chat-based interaction, and (3) autonomous model construction that leverages expert-labeled data with LLM-driven hyperparameter optimization. Through this design, AEGIS fosters continuous interaction in which the platform provides insights while experts guide model improvement, ensuring user intent is reflected and robustness is maintained under evolving data distributions.
Zitieren
APA
Kim, D., Sim, Y. S., Yoon, S., Yoon, S., Yoa, S., Lee, S., & Lim, W. (2026). AEGIS: Toward Expert-in-the-loop Industrial Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41619-41621. https://doi.org/10.1609/aaai.v40i48.42359
Vancouver
Kim D, Sim YS, Yoon S, Yoon S, Yoa S, Lee S, et al. AEGIS: Toward Expert-in-the-loop Industrial Anomaly Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41619-41621. doi:10.1609/aaai.v40i48.42359
BibTeX
@article{Kim2026,
author = {Kim, Dongmin and Sim, Ye Seul and Yoon, Suhee and Yoon, Sanghyu and Yoa, Seungdong and Lee, Soonyoung and Lim, Woohyung},
title = {AEGIS: Toward Expert-in-the-loop Industrial Anomaly Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41619--41621},
doi = {10.1609/aaai.v40i48.42359}
}
EUVIMED