In this study, we investigate system-level emergent risks of interacting AI agents. The core contribution of this work is an exploratory scenario-based identification of these risks as well as their categorization. We consider a multitude of systemic risk examples from existing literature and develop two scenarios demonstrating emergent risk patterns in domains of smart grid and social welfare. We provide a taxonomy of identified risks that categorizes them in different groups. In addition, we make two other important contributions: first, we identify what emergent behavior types produce systemic risks, and second, we develop a graphical language "Agentology" for visualization of interacting AI systems. Our study opens a new research direction for system-level risks of interacting AI, and is the first to closely investigate them.
@article{arxiv.2512.17793,
title = {Systemic Risks of Interacting AI},
author = {Paul Darius and Thomas Hoppe and Andrei Aleksandrov},
journal= {arXiv preprint arXiv:2512.17793},
year = {2025}
}