Gianni Molinari, Fabio Ciravegna
The rapid advancement of intelligent agents and Large Language Models (LLMs) is reshaping the computing field. Their ability to perceive, reason, and act through natural language understanding enables autonomous problem-solving in heterogeneousenvironments, including the management of sensors, devices, and data. This survey outlines the architectural components of LLM agents (profiling, memory, planning, and action) and examines their deployment and evaluation across various scenarios. Then it reviews computational advancements (cloud to edge) in pervasive computing , the ubiquitous embedding of interconnected sensors and devices into the physical world, and how AI is moving in this field. It highlights state-of-the-art agent deployment strategies and applications, including local and distributed execution on resource-constrained devices. This survey identifies key challenges of these agents in pervasive computing such as architectural, energetic and privacy limitations. It finally proposes what we called “ Agent as a Tool ”, a conceptual framework for pervasive agentic AI, emphasizing context awareness, modularity, security, efficiency and effectiveness.