A Framework for AI-Native Semantic-Based Dynamic Slicing for 6G Networks

2025-10-12

AI Summary

To address the challenges of resource optimization and the decoupling of data processing from network operations in ultra-dense, dynamic 6G networks, this paper proposes an AI-native semantic slicing framework—the first to deeply integrate semantic communication with network slicing. The framework enables multi-layered, dynamic resource partitioning based on semantic context, establishing a cross-layer collaborative computing continuum spanning communication, computation, and AI. Leveraging a unified physical and data infrastructure, it supports semantic-level data distillation and on-demand transmission. Compared to conventional static slicing, our approach significantly improves resource utilization and system flexibility. It provides a scalable architectural foundation for AI-driven, adaptive services in 6G networks, advancing the paradigm of context-aware, semantics-guided networking.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Search and Optimization: Distributed Search
• Computer Vision: Remote Sensing / Geospatial AI

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

In the ensuing ultra-dense and diverse environment in future ac{6G} communication networks, it will be critical to optimize network resources via mechanisms that recognize and cater to the diversity, density, and dynamicity of system changes. However, coping with such environments cannot be done through the current network approach of compartmentalizing data as distinct from network operations. Instead, we envision a computing continuum where the content of the transmitted data is considered as an essential element in the transmission of that data, with data sources and streams analyzed and distilled to their essential elements, based on their semantic context, and then processed and transmitted over dedicated slices of network resources. By exploiting the rich content and semantics within data for dynamic and autonomous optimization of the computing continuum, this article opens the door to integrating communication, computing, cyber-physical systems, data flow, and AI, presenting new and exciting opportunities for cross-layer design. We propose semantic slicing, a two-pronged approach that builds multiple virtual divisions within a single physical and data infrastructure, each with its own distinct characteristics and needs. We view semantic slicing as a novel shift from current static slicing techniques, extending existing slicing approaches such that it can be applied dynamically at different levels and categories of resources in the computing continuum. Further it propels the advancement of semantic communication via the proposed architectural framework.

Problem

• Optimizing network resources for ultra-dense dynamic 6G environments
• Integrating data semantics with network operations for efficiency
• Developing dynamic semantic slicing to replace static network approaches

Innovation

• AI-native semantic slicing for 6G networks
• Dynamic resource allocation using data semantics
• Integrated computing continuum with cross-layer design