From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Xiaolei, Zhou, Lu, Xu, Xiaogang, Wu, Jiafei, Du, Tianyu, Huang, Heqing, Peng, Hao, Liu, Zhe
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908904733016064
author Zhang, Xiaolei
Zhou, Lu
Xu, Xiaogang
Wu, Jiafei
Du, Tianyu
Huang, Heqing
Peng, Hao
Liu, Zhe
author_facet Zhang, Xiaolei
Zhou, Lu
Xu, Xiaogang
Wu, Jiafei
Du, Tianyu
Huang, Heqing
Peng, Hao
Liu, Zhe
contents 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 development of multilayered, autonomy-aware defense architectures for trustworthy AI agent systems.
format Preprint
id arxiv_https___arxiv_org_abs_2603_07496
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
Zhang, Xiaolei
Zhou, Lu
Xu, Xiaogang
Wu, Jiafei
Du, Tianyu
Huang, Heqing
Peng, Hao
Liu, Zhe
Cryptography and Security
Artificial Intelligence
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 development of multilayered, autonomy-aware defense architectures for trustworthy AI agent systems.
title From Thinker to Society: Security in Hierarchical Autonomy Evolution of AI Agents
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2603.07496