From Stateless Queries to Autonomous Actions: A Layered Security Framework for Agentic AI Systems

Abstract

Agentic AI systems face security challenges that stateless large language models do not. They plan across extended horizons, maintain persistent memory, invoke external tools, and coordinate with peer agents. Existing security analyses organize threats by attack type (prompt injection, jailbreaking), but provide no principled model of which architectural component is vulnerable or over what timescale the threat manifests. This paper makes five contributions. First, we introduce the Layered Attac

Categories

Framework mappings

Suggested from the entry's categories.

@misc{chu2026froma,
  title = {{From Stateless Queries to Autonomous Actions: A Layered Security Framework for Agentic AI Systems}},
  author = {Kexin Chu},
  year = {2026},
  month = apr,
  eprint = {2604.23338},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.23338}
}