When Agentic AI Meets Integrated Sensing and Communication

The survey, posted as arXiv:2608.05792v1, argues that agentic AI is evolving Integrated Sensing and Communication (ISAC) from a purely function-oriented physical-layer technology into a goal-driven, closed-loop intelligent system, termed AISAC. The authors note that prior research on learning-based sensing, resource allocation, reconfigurable intelligent surfaces (RIS), edge intelligence, multi-agent coordination, and resilient networking has largely been siloed. To unify these threads, they propose a six-stage closed-loop framework—observation, contextualization, reasoning and prediction, planning and orchestration, execution and collaboration, and feedback and resilience—and introduce five levels of agentic maturity, from physical-layer primitives to fully closed-loop agentic ISAC.