RFAmpDesigner: A Self-Evolving Multi-Agent LLM Framework for Automated Radio Frequency Amplifier Design

TL;DR

This paper introduces RFAmpDesigner, a multi-agent framework utilizing LLMs and resource allocation to automate RF amplifier design, improving data efficiency and transferability.

Contribution

It presents the first LLM-driven RF amplifier sizing approach that incorporates domain knowledge and self-evolving optimization via retrieval-augmented generation.

Findings

Successfully designed low noise amplifiers with 10-80% bandwidths.

Demonstrated the framework's ability to operate across GHz frequency ranges.

Showed improved design automation and knowledge reuse in RF engineering.

Abstract

Automating radio frequency (RF) amplifier design remains challenging because existing methods suffer from the curse of dimensionality, weak use of domain knowledge, and poor transferability, leading to low data efficiency. Meanwhile, although large language models (LLMs) have shown promise in many scientific domains, applying them directly to RF sizing is nontrivial due to the numerical nature of circuit optimization and the reliance on domain-specific design flows. To address this, this paper proposes RFAmpDesigner, a multi-agent framework that automates RF amplifier sizing. It introduces a resource-allocation middleware that reframes high-dimensional parameter tuning as a low-dimensional resource distribution problem, making it easier to inject sizing knowledge into general-purpose LLMs. The framework also follows standard design practice, enabling LLMs to distinguish between high- and low-cost actions and search in parallel. To realize a self-evolving optimization process, the framework employs retrieval-augmented generation (RAG) to reuse past knowledge and experience from memory base. As a proof of concept, we apply RFAmpDesigner to low noise amplifiers of varying complexity. The experimental results show that it can automatically synthesize designs with fractional bandwidths ranging from 10\% to 80\% and center frequencies from 10 GHz to 50 GHz. To the best of our knowledge, this work develops the first LLM-driven approach for RF amplifier sizing that operates on design concepts instead of treating netlists as text, offering a novel solution to mitigate data scarcity in RF design.