# Codebook-Based Solutions for Reconfigurable Intelligent Surfaces and Their Open Challenges

arXiv: https://arxiv.org/abs/2211.05976 · HTML: https://mlsanity.com/paper/2211.05976/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Nov 2022.

## Built on by (most cited first, 2 of 2)

- [Learning Beamforming Codebooks for Active Sensing with Reconfigurable Intelligent Surface](https://mlsanity.com/paper/2503.19046/) (2025)
- [Learning to Reflect: Hierarchical Multi-Agent Reinforcement Learning for CSI-Free mmWave Beam-Focusing](https://mlsanity.com/paper/2603.07370/) (2026)

## Abstract (arXiv)

Reconfigurable intelligent surfaces (RIS) is a revolutionary technology to cost-effectively improve the performance of wireless networks. We first review the existing framework of channel estimation and passive beamforming (CE & PBF) in RIS-assisted communication systems. To reduce the excessive pilot signaling overhead and implementation complexity of the CE & PBF framework, we conceive a codebook-based framework to strike flexible tradeoffs between communication performance and signaling overhead. Moreover, we provide useful insights into the codebook design and learning mechanisms of the RIS reflection pattern. Finally, we analyze the scalability of the proposed framework by flexibly adapting the training overhead to the specified quality-of-service requirements and then elaborate on its appealing advantages over the existing CE & PBF approaches. It is shown that our novel codebook-based framework can be beneficially applied to all RIS-assisted scenarios and avoids the curse of model dependency faced by its existing counterparts, thus constituting a competitive solution for practical RIS-assisted communication systems.