{"ID":2827201,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17793","arxiv_id":"2512.17793","title":"Systemic Risks of Interacting AI","abstract":"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.","short_abstract":"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 demo...","url_abs":"https://arxiv.org/abs/2512.17793","url_pdf":"https://arxiv.org/pdf/2512.17793v1","authors":"[\"Paul Darius\",\"Thomas Hoppe\",\"Andrei Aleksandrov\"]","published":"2025-12-19T16:59:53Z","proceeding":"cs.CY","tasks":"[\"cs.CY\"]","methods":"[\"LoRA\"]","has_code":false}