Generative Communications: Overview, Technologies, and Trends

2026-07-10

AI Summary

Traditional communication systems prioritize bit-level accurate transmission, which struggles to meet the 6G requirements for semantic understanding and efficient content delivery. This work proposes a novel paradigm—generative communication (GenCom)—that deeply integrates large AI models into the communication process for the first time. By leveraging shared generative priors and knowledge bases, GenCom enables the receiver to reconstruct target content from minimal transmitted information through controlled generation, effectively realizing “communication as generation.” The proposed two-tier GenCom architecture synergistically combines semantic understanding, generative priors, and large-model capabilities. Experimental validation across four representative scenarios demonstrates its potential for ultra-efficient transmission, semantic-level robustness, and novel network functionalities, offering an AI-native, generation-driven technical pathway for 6G.

Abstract

The groundbreaking development of generative artificial intelligence (AI) is rapidly boosting the ability to generate content such as images and videos, reshaping communication paradigms. This article introduces generative communications (GenCom), a novel paradigm for 6G networks in which large AI models (LAMs) drive semantic understanding, reasoning, and content generation, embedding these into the communication process. Unlike traditional systems that strictly pursue accurate bit transmission, GenCom enables transmitters to convey only minimal yet sufficient information, while receivers leverage shared generative priors and knowledge bases to synthesize the intended output. Communication is thus redefined as controlled generation rather than data reproduction. We formalize the concept of GenCom, clarify its AI-native and generation-driven properties, and present its core mechanisms. A two-layer GenCom architecture supported by key enabling technologies is proposed, and analysis of four representative application scenarios demonstrates that GenCom offers ultra-efficient transmission, semantic-level robustness, and new network functions. Finally, we outline future research directions, including foundational theory and real-time processing, highlighting a promising pathway toward 6G networks.

Problem

• generative communications
• 6G networks
• semantic communication
• large AI models
• efficient transmission

Innovation

• Generative Communications
• Large AI Models
• Semantic Communication
• 6G Networks
• Controlled Generation