Rich-ARQ: From 1-bit Acknowledgment to Rich Neural Coded Feedback

2026-02-08

AI Summary

This work addresses the limitation of traditional wireless communication systems, where 1-bit ACK/NACK feedback provides insufficient information for efficient physical-layer cooperative coding. To overcome this, the authors propose Rich-ARQ, a novel framework that replaces conventional 1-bit feedback with high-dimensional neural codes to enable proactive transmitter–receiver collaboration at the physical layer. Key innovations include the first asynchronous neural feedback code supporting dynamic channel adaptation and non-blocking transmission, a lightweight neural encoder architecture with decoupled AI–RF timing, and a full-stack prototype implemented on a standards-compliant software-defined radio (SDR) platform. Over-the-air experiments demonstrate that Rich-ARQ significantly improves SNR, substantially reduces latency, and outperforms existing learning-based feedback schemes compared to conventional HARQ.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Multiagent Systems: Agent Communication
• Machine Learning: Hardware-aware ML

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

This paper reimagines the foundational feedback mechanism in wireless communication, transforming the prevailing 1-bit binary ACK/NACK with a high-dimensional, information-rich vector to transform passive acknowledgment into an active collaboration. We present Rich-ARQ, a paradigm that introduces neural-coded feedback for collaborative physical-layer channel coding between transmitter and receiver. To realize this vision in practice, we develop a novel asynchronous feedback code that eliminates stalling from feedback delays, adapts dynamically to channel fluctuations, and features a lightweight encoder suitable for on-device deployment. We materialize this concept into the first full-stack, standard-compliant software-defined radio prototype, which decouples AI inference from strict radio timing. Comprehensive over-the-air experiments demonstrate that Rich-ARQ achieves significant SNR gains over conventional 1-bit hybrid ARQ and remarkable latency reduction over prior learning-based feedback codes, moving the promise of intelligent feedback from theory to a practical, high-performance reality for next-generation networks.

Problem

• wireless communication
• ACK/NACK feedback
• channel coding
• feedback mechanism
• physical-layer collaboration

Innovation

• neural-coded feedback
• asynchronous feedback code
• software-defined radio
• collaborative channel coding
• intelligent ARQ