Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems

Abstract

Traditional operating systems were designed around deterministic programs, explicit control flow, and human initiated workflows. Their core abstractions processes, threads, system calls, files, and permissions assume bounded behavior and predictable interaction patterns. Agentic AI systems introduce a different execution model: long-lived, goal-directed entities that reason probabilistically, invoke tools dynamically, and adapt behavior based on feedback. While agents can be implemented as user-

Categories

@misc{sharma2026agent,
  title = {{Agent Operating Systems (AOS): Integrating Agentic Control Planes into, and Beyond, Traditional Operating Systems}},
  author = {Ankur Sharma and Deep Shah},
  year = {2026},
  month = jun,
  eprint = {2606.01508},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2606.01508}
}