From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
Xiaolei Zhang, Lu Zhou, Xiaogang Xu, Jiafei Wu, Tianyu Du, Heqing Huang, Hao Peng, Zhe Liu

TL;DR
This paper introduces the Hierarchical Autonomy Evolution framework for AI agents, categorizing security vulnerabilities across three levels of autonomy and proposing a taxonomy to guide the development of robust defense mechanisms.
Contribution
It presents a novel hierarchical framework and threat taxonomy for AI agent security, addressing gaps in existing defenses and guiding future trustworthy AI development.
Findings
Identifies three tiers of autonomy with distinct security challenges
Provides a comprehensive taxonomy of threats including cognitive, physical, and systemic risks
Evaluates current defenses and highlights research gaps
Abstract
Artificial Intelligence (AI) agents have evolved from passive predictive tools into active entities capable of autonomous decision-making and environmental interaction, driven by the reasoning capabilities of Large Language Models (LLMs). However, this evolution has introduced critical security vulnerabilities that existing frameworks fail to address. The Hierarchical Autonomy Evolution (HAE) framework organizes agent security into three tiers: Cognitive Autonomy (L1) targets internal reasoning integrity; Execution Autonomy (L2) covers tool-mediated environmental interaction; Collective Autonomy (L3) addresses systemic risks in multi-agent ecosystems. We present a taxonomy of threats spanning cognitive manipulation, physical environment disruption, and multi-agent systemic failures, and evaluate existing defenses while identifying key research gaps. The findings aim to guide the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdversarial Robustness in Machine Learning · Explainable Artificial Intelligence (XAI) · Multi-Agent Systems and Negotiation
