TY - JOUR
T1 - Generative AI-Empowered Signal Processing for Collaborative Embodied Agents
T2 - A Survey on Agentic Security
AU - Pan, Gaofeng
AU - Tao, Yi
AU - Yang, Ziyi
AU - Li, Junnan
AU - Peng, Yuanyuan
AU - Bao, Xuemin
AU - Zhang, Yiyang
AU - Hua, Zizheng
AU - Wang, Shuai
AU - Zhang, Rui
AU - Du, Changhao
N1 - Publisher Copyright:
© 2026 IEEE. All rights reserved.
PY - 2026
Y1 - 2026
N2 - The transition from the Internet of Things (IoT) to the Internet of Agents (IoA) necessitates a fundamental paradigm shift in physical layer security, moving from static, rule-based defenses toward autonomous, agentic resilience. However, current embodied nodes often lack the cognitive capability required to handle adaptive, intelligent threats. We propose employing Generative AI (GAI) as the cognitive engine—rather than merely a signal processing tool—to empower agents to construct an internal world model of the physical environment. In this work, we present a holistic agentic security framework that instills autonomy across two key dimensions. First, Endogenous Self-Evolution allows agents to utilize GAI for predictive environmental modeling and autonomous resource decision-making, thereby self-calibrating against hardware impairments. Second, Exogenous Active Defense implements a generative observe-orient-decide-act (OODA) loop. This loop enables agents to autonomously execute intelligent threat perception, confrontation planning, and a strategic duality of behavioral concealment and identity camouflage. Finally, we discuss the path toward general-purpose security agents via neuro-symbolic architectures. This survey bridges the gap between signal generation and agentic reasoning, defining a new era where security becomes an innate, evolving property of collaborative embodied intelligence.
AB - The transition from the Internet of Things (IoT) to the Internet of Agents (IoA) necessitates a fundamental paradigm shift in physical layer security, moving from static, rule-based defenses toward autonomous, agentic resilience. However, current embodied nodes often lack the cognitive capability required to handle adaptive, intelligent threats. We propose employing Generative AI (GAI) as the cognitive engine—rather than merely a signal processing tool—to empower agents to construct an internal world model of the physical environment. In this work, we present a holistic agentic security framework that instills autonomy across two key dimensions. First, Endogenous Self-Evolution allows agents to utilize GAI for predictive environmental modeling and autonomous resource decision-making, thereby self-calibrating against hardware impairments. Second, Exogenous Active Defense implements a generative observe-orient-decide-act (OODA) loop. This loop enables agents to autonomously execute intelligent threat perception, confrontation planning, and a strategic duality of behavioral concealment and identity camouflage. Finally, we discuss the path toward general-purpose security agents via neuro-symbolic architectures. This survey bridges the gap between signal generation and agentic reasoning, defining a new era where security becomes an innate, evolving property of collaborative embodied intelligence.
KW - Adversarial defense
KW - CSI compression
KW - agentic AI
KW - anomaly detection
KW - channel prediction
KW - generative AI
KW - hardware impairments
KW - secure communications
UR - https://www.scopus.com/pages/publications/105034222947
U2 - 10.1109/TCCN.2026.3676045
DO - 10.1109/TCCN.2026.3676045
M3 - Article
AN - SCOPUS:105034222947
SN - 2332-7731
VL - 12
SP - 6741
EP - 6759
JO - IEEE Transactions on Cognitive Communications and Networking
JF - IEEE Transactions on Cognitive Communications and Networking
ER -