PERA: A Perceive-Reason-Act Interface Bridging Sensing, Cognitive Reasoning, and Trustworthy Agentic Response for 6G
Networking and Internet Architecture
Summary
The authors propose a new way to make future wireless networks smarter and more autonomous by combining large language models (LLMs) and wireless data into a unified system called Generative Network Intelligence. Their PERA approach lets the network perceive its state, reason about it, and act accordingly, which helps manage complex tasks more efficiently than traditional machine learning methods. They introduce a three-layer design suitable for devices with limited resources and show through a case study how their system can improve wireless link monitoring and beam control with understandable explanations. This work aims to create more trusted and flexible network intelligence.
Authors
Mohammad Farzanullah, Melike Erol-Kantarci, Lajos Hanzo
Abstract
The realization of next-generation (NG) networks hinges on a fundamental departure from preprogrammed protocol engineering towards a paradigm of self-consciously evolving, autonomous and trusted intelligence. While conventional machine learning (ML) has introduced localized automation, it remains inherently bounded by single-task processing pipelines incapable of handling complex cross-layer dynamics. As a partial remedy, large language models (LLMs) excel at generalized cognitive reasoning, but to a degree they remain detached from the rich modalities of wireless telemetry. As a solution, we unveil Generative Network Intelligence conceptualized via the Perceive-Reason-Act (PERA) paradigm. This paradigm treats the wireless channel and the underlying network states as a continuous, multimodal narrative. By synchronizing the perceptual grounding of Large Wireless AI Models (LWAMs) with the cognitive reasoning of LLMs, PERA heralds the era of native NG intelligence. Crucially, this unified intelligence replaces fragmented, task-specific edge models by an efficient multi-task architecture delivering the real-time control needed for supporting dynamic physical applications while reducing both the complexity and energy dissipation. Moreover, we contrast the structural limitations of traditional ML to generative paradigms, conceive agentic reasoning across a NG protocol stack, and detail a practical three-tier design specifically engineered for the resource-constrained wireless edge. This architectural paradigm serves as a foundational framework for realizing fully autonomous, embodied agentic AI in NG networks. To validate this vision, our case study evaluates link-state classification and beam prediction, demonstrating how grounding wireless telemetry within a cognitive engine delivers the transparent, human-readable rationales required for trusted physical-layer diagnostics and beam control.