LLM-based Visual Code Completion for Aerospace Geometric Design
2026-06-15 • Computation and Language
Computation and Language
AI summaryⓘ
The authors developed a new AI helper tool using GPT 5.4 that assists aerospace engineers with designing aircraft parts through a visual programming method. They created a special plugin called Wingbuilder and a dataset of expert design tasks to test the tool. Two experienced aerospace engineers tried the tool and found its suggestions helpful, especially for complex tasks, but the AI could be slow to respond. The engineers liked the tool and said they would consider using it in the future. Overall, the authors show that this AI approach can support aerospace design work with more explainable and safety-focused methods.
Large Language Models (LLMs)Vision Language Models (VLMs)Visual Code CompletionReAct MethodologyGrasshopper PluginAerospace GeometryGPT 5.4Visual ProgrammingCopilot AIUser Trial Evaluation
Authors
Hau Kit Yong, Robert Marsh, Edmar A. Silva, András Sóbester, Stuart E. Middleton
Abstract
Recent advances in both Large Language Models (LLMs) and Vision Language Models (VLMs) have seen a step change in their ability to perform visual code completion, but the aerospace industry, which prioritizes safety and explainabilty over rapid LLM adoption, currently has no publicly announced LLM-based geometric design copilot systems in commercial use by aerospace Original Equipment Manufacturers (OEMs). This paper presents a LLM-based visual programming copilot application for aerospace engineering design tasks, using a visual programming variant of the ReAct methodology and GPT 5.4. In addition to the copilot, we describe Wingbuilder, a new Grasshopper plugin library with custom components for aerospace-specific geometry abstraction, and an associated Aerospace Visual Programming Dataset (AVPD) with 18 aerospace expert designed tasks at different levels of difficulty alongside ground truth solutions. We evaluate our copilot application with a user trial involving two experienced aerospace engineers from a large aircraft manufacturing company. We find our copilot visual programming ReAct methodology was successful in generating suggestions that participants found helpful, but slow ReAct inference times limit its usefulness to more complex time-consuming tasks where waiting for good copilot solution suggestion was worthwhile. Participants reported they liked the tool and would be willing to use it in the future.