LEAM: A Prompt-only Large Language Model-enabled Antenna Modeling Method

2025-04-25

AI Summary

Antenna modeling traditionally relies heavily on expert knowledge and involves labor-intensive, iterative workflows, severely hindering design efficiency. To address this, we propose LEAM—a prompt-driven antenna modeling paradigm leveraging large language models (LLMs) without fine-tuning or training. LEAM enables end-to-end generation of parameterized electromagnetic models directly from heterogeneous inputs—including natural language specifications, antenna images, and technical text from patents or papers—using only carefully engineered multimodal prompts. The approach integrates LLM-based semantic understanding with domain-specific electromagnetic structural priors and interfaces with Antenna Toolbox as well as commercial simulators (CST Studio Suite and ANSYS HFSS) to export simulation-ready models. Evaluated on three canonical antenna types—Vivaldi, slotted patch, and monopole-slotted antennas—LEAM consistently produces correct, simulatable models within minutes, dramatically accelerating design iteration.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Cognitive Modeling & Cognitive Systems: Analogy

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Antenna modeling is a time-consuming and complex process, decreasing the speed of antenna analysis and design. In this paper, a large language model (LLM)- enabled antenna modeling method, called LEAM, is presented to address this challenge. LEAM enables automatic antenna model generation based on language descriptions via prompt input, images, descriptions from academic papers, patents, and technical reports (either one or multiple). The effectiveness of LEAM is demonstrated by three examples: a Vivaldi antenna generated from a complete user description, a slotted patch antenna generated from an incomplete user description and the operating frequency, and a monopole slotted antenna generated from images and descriptions scanned from the literature. For all the examples, correct antenna models are generated in a few minutes. The code can be accessed via https://github.com/TaoWu974/LEAM.

Problem

• Automates antenna modeling from language descriptions
• Reduces time for antenna design and analysis
• Generates models from text, images, or mixed inputs

Innovation

• LLM-enabled automatic antenna model generation
• Supports prompt input, images, and descriptions
• Generates correct models in minutes