Token Communications (TokCom): A Unified AI-Native Communication Framework

2026-07-20

AI Summary

This work addresses the limitations of the traditional Shannon communication paradigm, which emphasizes bit-level reliability yet falls short in supporting the semantic and task-oriented communication demands of AI agents in 6G networks. To bridge this gap, the paper proposes Token Communications (TokCom), a novel framework that elevates the token—a fundamental unit from large language models (LLMs)—to the primary information exchange primitive in 6G, thereby establishing an AI-native communication architecture. The framework further introduces a token-sharing mechanism enabling interoperability across heterogeneous LLMs. Experimental results demonstrate TokCom’s feasibility in efficiently conveying semantic information between diverse models, significantly enhancing collaborative reasoning among AI agents and offering a unified foundation for the evolution of 6G toward semantic- and task-driven communication paradigms.

Abstract

As artificial intelligence (AI) evolves from static perception to generative reasoning and autonomous agency, the fundamental principles of wireless communications are undergoing a paradigm shift. The classical Shannon paradigm, centered on reliable bit-level reconstruction for users, is increasingly misaligned with an emerging scenario in which the primary users of the network are interconnected AI agents. This article introduces token communications (TokCom), a novel framework that elevates tokens, i.e., the fundamental processing units of large language models (LLMs), to first-class entities for information exchange in the sixth generation wireless cellular networks (6G). We first examine the architectural transition from conventional communication systems to TokCom and identify the key challenges in implementing this transition, along with potential solution approaches. Thereafter, we present a practical case study to demonstrate the effectiveness of token sharing among heterogeneous language models. Finally, we outline promising future research directions toward realizing an AI-native, token-driven communication paradigm suitable for 6G.

Problem

• AI-native communication
• token communications
• 6G
• LLM tokens
• Shannon paradigm

Innovation

• Token Communications
• AI-native
• 6G
• Large Language Models
• Semantic Communication