Reasoning Meets Representation: Envisioning Neuro-Symbolic Wireless Foundation Models
Jaron Fontaine, Mohammad Cheraghinia, John Strassner, Adnan Shahid, Eli De Poorter
TL;DR
The paper addresses the need for trustworthy, explainable wireless AI by combining neural RF representations with symbolic reasoning to satisfy physical and regulatory constraints. It proposes a Neuro-Symbolic Wireless AI framework that uses a WPFM neural perception engine, an ontology-backed knowledge graph, and differentiable logic to enable end-to-end trainable reasoning. Key contributions include a modular architecture that decouples perception and reasoning, a differentiable logic layer for verifiable inference, and a roadmap of challenges such as real-time constraints and bridging sub-symbolic to symbolic representations. This approach aims to enable AI-native 6G networks with proactive resource management, robust interpretability, and compliance across spectrum policies.
Abstract
Recent advances in Wireless Physical Layer Foundation Models (WPFMs) promise a new paradigm of universal Radio Frequency (RF) representations. However, these models inherit critical limitations found in deep learning such as the lack of explainability, robustness, adaptability, and verifiable compliance with physical and regulatory constraints. In addition, the vision for an AI-native 6G network demands a level of intelligence that is deeply embedded into the systems and is trustworthy. In this vision paper, we argue that the neuro-symbolic paradigm, which integrates data-driven neural networks with rule- and logic-based symbolic reasoning, is essential for bridging this gap. We envision a novel Neuro-Symbolic framework that integrates universal RF embeddings with symbolic knowledge graphs and differentiable logic layers. This hybrid approach enables models to learn from large datasets while reasoning over explicit domain knowledge, enabling trustworthy, generalizable, and efficient wireless AI that can meet the demands of future networks.