AI-Native 6G Physical Layer with Cross-Module Optimization and Cooperative Control Agents

TL;DR

This work tackles the suboptimality of modular wireless designs by proposing an AI-native cross-module optimization framework (CMO-CCA) for 6G, enabling end-to-end learning across uplink JSCC/ modulation and downlink modulation/precoding with cooperative control agents. It introduces three key enhancements: cross-layer modulation to expand the downlink constellation space, utility-oriented precoding that directly optimizes end-to-end performance, and modulation-enabled CSI feedback to avoid bit-level bottlenecks, all within a differentiable training pipeline and three-stage learning strategy. Theoretical analysis connects the proposed cross-layer modulation to information-theoretic capacity through BICM concepts, while extensive simulations under practical 3GPP channel assumptions show BLER and throughput gains over 5G baselines, including robustness under imperfect uplink feedback and interference. The framework also discusses standardization implications, highlighting the need for joint layer design, model alignment, and AI-driven LCM approaches to realize these gains in future networks.

Abstract

In this article, a framework of AI-native cross-module optimized physical layer with cooperative control agents is proposed, which involves optimization across global AI/ML modules of the physical layer with innovative design of multiple enhancement mechanisms and control strategies. Specifically, it achieves simultaneous optimization across global modules of uplink AI/ML-based joint source-channel coding with modulation, and downlink AI/ML-based modulation with precoding and corresponding data detection, reducing traditional inter-module information barriers to facilitate end-to-end optimization toward global objectives. Moreover, multiple enhancement mechanisms are also proposed, including i) an AI/ML-based cross-layer modulation approach with theoretical analysis for downlink transmission that breaks the isolation of inter-layer features to expand the solution space for determining improved constellation, ii) a utility-oriented precoder construction method that shifts the role of the AI/ML-based CSI feedback decoder from recovering the original CSI to directly generating precoding matrices aiming to improve end-to-end performance, and iii) incorporating modulation into AI/ML-based CSI feedback to bypass bit-level bottlenecks that introduce quantization errors, non-differentiable gradients, and limitations in constellation solution spaces. Furthermore, AI/ML based control agents for optimized transmission schemes are proposed that leverage AI/ML to perform model switching according to channel state, thereby enabling integrated control for global throughput optimization. Finally, simulation results demonstrate the superiority of the proposed solutions in terms of BLER and throughput. These extensive simulations employ more practical assumptions that are aligned with the requirements of the 3GPP, which hopefully provides valuable insights for future standardization discussions.

Figures (6)

• Figure 1: Illustration of proposed AI-native framework
• Figure 2: Illustration of proposed AI-native cross-module optimized transmission scheme.
• Figure 3: Performance comparison under idealized uplink transmission
• Figure 4: Performance comparison under practical uplink transmission
• Figure 5: Generalization study of proposed scheme for different channel models