Understanding Cognition-Induced Risks in Agentic AI Systems

Abstract:Frontier agentic systems powered by large language models (LLMs) exhibit human-like patterns of cognition. As these systems become deeply integrated across different domains, their cognitive engagement raises critical concerns for human society that remain insufficiently studied. To address this gap, we systematically analyze risks induced by expanding cognitive capabilities, following a three-level framework defined by their cognitive scope, from physical cognition to social cognition, and finally to self-referential cognition. We study their potential risks to human agency, autonomy, and control capability, corresponding to each cognitive level. We finally propose strategies to mitigate these risks and enhance the controllability of agentic AI systems, ensuring their long-term safe development.

This paper has been accepted by IEEE Intelligent Systems, which can be accessed at this https URL. The DOI is https://doi.org/10.1109/MIS.2026.3721766

Artificial Intelligence (cs.AI)

arXiv:2608.15304 [cs.AI]

(or arXiv:2608.15304v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2608.15304 arXiv-issued DOI via DataCite (pending registration)

https://doi.org/10.1109/MIS.2026.3721766 DOI(s) linking to related resources