Inference-Driven Uplink for 6G: Architecture, Principles, and Challenges

TL;DR

This paper proposes InferCom, an inference-driven uplink architecture for 6G that leverages AI models and task-agnostic compression to improve transmission efficiency under low SNR conditions.

Contribution

It introduces a novel compute-asymmetric architecture with AI-enabled receivers and QoE-aware retransmission, grounded in information bottleneck theory, to enhance 6G uplink performance.

Findings

InferCom reduces transmitter complexity compared to 5G NR.

It achieves lower required SNRs for reliable transmission.

InferCom improves retransmission efficiency over existing methods.

Abstract

Next-generation wireless networks (6G) face a critical uplink challenge arising from stringent device-side resource constraints and the growing demand for intelligence services. This article introduces InferCom, an inference-driven communication architecture designed to enable robust 6G uplink transmission under low signal-to-noise (SNR) conditions. InferCom adopts a compute-asymmetric architecture, featuring a lightweight transmitter and an inference-capable receiver empowered by generative artificial intelligence (GenAI) models, together with a quality-of-experience (QoE)-aware retransmission mechanism. Grounded in the information bottleneck (IB) theory, InferCom redefines uplink communications through task-agnostic compression, inference-driven reconstruction, error-distribution channel coding, and QoE-aware feedback. The case study demonstrates that InferCom outperforms conventional 5G NR and Deep- JSCC in terms of transmitter-side computational complexity, required SNRs and retransmission efficiency. Finally, we outline key challenges and research directions toward making InferCom a practical enabler of human-centric, intelligent and sustainable wireless networks.