When Agentic AI Meets Integrated Sensing and Communication

2026-08-06

AI Summary

Current research on integrated sensing and communication (ISAC) remains fragmented across perception, resource allocation, and intelligent decision-making, lacking a goal-driven, closed-loop intelligent framework. This work proposes the AISAC paradigm, introducing a novel agent-based closed-loop architecture comprising six stages: observation, contextualization, reasoning and prediction, planning and orchestration, execution and collaboration, and feedback resilience. It further defines a five-level agent maturity model and systematically evaluates existing approaches against nine core agent capabilities, revealing that most satisfy only one or two criteria. The analysis underscores critical challenges—particularly physical-semantic alignment and real-time agent-physical layer interaction—and advances ISAC toward autonomous intelligence by integrating multimodal AI, large language models, reinforcement learning, and federated learning.

Abstract

Agentic artificial intelligence (AI) is transforming Integrated Sensing and Communication (ISAC) from a function-oriented physical-layer technology into a goal-driven, closed-loop intelligent system, a paradigm we term AISAC. Existing work on learning-based sensing, resource allocation, reconfigurable intelligent surfaces (RIS), edge intelligence, multi-agent coordination, and resilient networking has developed largely in isolation. This survey unifies the literature within a six-stage closed-loop framework comprising observation, contextualization, reasoning and prediction, planning and orchestration, execution and collaboration, and feedback and resilience. It also introduces five levels of agentic maturity, ranging from physical-layer primitives to fully closed-loop agentic ISAC. We use this framework to review advances in multimodal intelligence, large language models, reinforcement learning, federated learning, RIS-assisted control, Unmanned Aerial Vehicle (UAV) and vehicular networks, and AI-native network management, and analyze privacy, security, resilience, and sustainability as cross-cutting requirements of the full perception-reasoning-action loop. An audit of representative studies against nine agentic-specific evaluation criteria shows that no system reports more than one or two of them, exposing a gap between claimed and demonstrated agentic maturity. We identify open challenges in physical-to-semantic grounding, predictive world models, real-time agent-PHY interaction, safe tool use, heterogeneous multi-agent collaboration, benchmarking, and resource-efficient autonomy.

Problem

• Agentic AI
• Integrated Sensing and Communication
• closed-loop intelligence
• multi-agent coordination
• AI-native networks

Innovation

• Agentic AI
• Integrated Sensing and Communication (ISAC)
• closed-loop intelligence
• multi-agent collaboration
• AI-native networking