Automation in Construction· 2026Q1
Integrating large language models for automated structural analysis
- 2citations
- Q1SCImago
- 2026year
Short summary
A new framework using domain-specific prompts and in-context learning enables Large Language Models (LLMs) to perform fully automated structural analysis from text descriptions to model outputs, achieving 100% accuracy with GPT-5.4 and GPT-4o on a benchmark dataset.
AI-generated from the title and abstract; the full text is not read.
Key points
- A framework is proposed for fully automated structural analysis using LLMs, integrating domain-specific prompts and in-context learning.
- The framework achieved 100% accuracy on a 20-problem benchmark dataset using GPT-5.4 and GPT-4o.
- GPT-4 achieved 85% accuracy, Gemini 1.5 Pro 80%, and Llama-3.3 30% on the same dataset.
- Domain-specific instructions improved performance by 30% for problems with asymmetrical configurations.
AI-generated from the title and abstract; the full text is not read.
Abstract
Automated analysis for engineering structures offers considerable potential for boosting efficiency by minimizing repetitive tasks. Although AI-driven methods are increasingly common, no systematic framework yet leverages Large Language Models (LLMs) for automatic structural analysis. This paper proposes a framework that employs domain-specific prompt design and in-context learning strategies to enhance LLM problem-solving capabilities and generative stability, enabling fully automated structural analysis from descriptive text to model outputs. A small-scale benchmark dataset consisting of 20 structural analysis word problems (SAWPs) is also introduced to evaluate the performance of different LLMs within the proposed framework. The results demonstrate that the proposed approach can increase the level of automation in solving SAWPs compared with traditional methods. Quantitatively, the framework built on GPT-5.4 and GPT-4o both achieved 100% accuracy, outperforming GPT-4 (85%), Gemini 1.5 Pro (80%), and Llama-3.3 (30%) on the test examples. Furthermore, integrating domain-specific instructions enhanced performance by 30% on problems with asymmetrical structural configurations.
The authors' abstract, as published at the source. Automation in Construction, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Software
SoftwareComputer Science