LLM-based Visual Code Completion for Aerospace Geometric Design

• URL: http://arxiv.org/abs/2606.16806v1
• Date: Mon, 15 Jun 2026 14:46:57 GMT
• Title: LLM-based Visual Code Completion for Aerospace Geometric Design
• Abstract summary: This paper presents a visual programming copilot application for aerospace engineering design tasks.<n>We use a visual programming variant of the ReAct methodology and GPT 5.4.<n>We evaluate our copilot application with a user trial involving two experienced aerospace engineers.
• Score: 1.8703452729758459
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• AeroGen: Agentic Drone Autonomy through Single-Shot Structured Prompting & Drone SDK [3.1941554288428193]
  AeroGen is an open-loop framework that enables consistently correct single-shot AI-generated drone control programs.<n>We show that AeroGen generates about 40 lines of AeroD Python code in about 20s per mission, in both real-world and simulations.
  arXiv  Detail & Related papers  (2026-03-15T06:16:02Z)
• From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence [150.3696990310269]
  Large language models (LLMs) have transformed automated software development by enabling direct translation of natural language descriptions into functional code.<n>We provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs.<n>We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder)
  arXiv  Detail & Related papers  (2025-11-23T17:09:34Z)
• Large Language Models as Autonomous Spacecraft Operators in Kerbal Space Program [42.87968485876435]
  Large Language Models (LLMs) are autonomous agents that take actions based on the content of the user text prompts.<n>We have developed a pure LLM-based solution for the Kerbal Space Program Differential Games (KSPDG) challenge.
  arXiv  Detail & Related papers  (2025-05-26T12:25:35Z)
• AGENT: An Aerial Vehicle Generation and Design Tool Using Large Language Models [13.674483311866183]
  AGENT learns powerful representations of aircraft designs directly from textual files.<n>AGENT can issue evaluations of designs allowing it to act as a surrogate model of the physics simulation that underlies the AircraftVerse dataset.
  arXiv  Detail & Related papers  (2025-04-11T21:13:10Z)
• LeRAAT: LLM-Enabled Real-Time Aviation Advisory Tool [29.306750550243894]
  This paper introduces LeRAAT, a framework that integrates large language models (LLMs) with the X-Plane flight simulator to deliver real-time, context-aware pilot assistance.<n>The system uses live flight data, weather conditions, and aircraft documentation to generate recommendations aligned with aviation best practices.
  arXiv  Detail & Related papers  (2025-03-05T05:34:15Z)
• OpenFly: A Comprehensive Platform for Aerial Vision-Language Navigation [49.697035403548966]
  Vision-Language Navigation (VLN) aims to guide agents by leveraging language instructions and visual cues, playing a pivotal role in embodied AI.<n>We propose OpenFly, a platform comprising various rendering engines, a versatile toolchain, and a large-scale benchmark for aerial VLN.<n>We construct a large-scale aerial VLN dataset with 100k trajectories, covering diverse heights and lengths across 18 scenes.
  arXiv  Detail & Related papers  (2025-02-25T09:57:18Z)
• Language Models are Spacecraft Operators [36.943670587532026]
  Large Language Models (LLMs) are autonomous agents that take actions based on the content of the user text prompts. We have developed a pure LLM-based solution for the Kerbal Space Program Differential Games (KSPDG) challenge.
  arXiv  Detail & Related papers  (2024-03-30T16:43:59Z)
• Octopus: Embodied Vision-Language Programmer from Environmental Feedback [58.04529328728999]
  Embodied vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. To bridge this gap, we introduce Octopus, an embodied vision-language programmer that uses executable code generation as a medium to connect planning and manipulation. Octopus is designed to 1) proficiently comprehend an agent's visual and textual task objectives, 2) formulate intricate action sequences, and 3) generate executable code.
  arXiv  Detail & Related papers  (2023-10-12T17:59:58Z)
• Improving aircraft performance using machine learning: a review [57.82442188072833]
  This review covers the new developments in machine learning (ML) that are impacting the multi-disciplinary area of aerospace engineering. We review the state of the art, gathering the advantages and challenges of ML methods across different aerospace disciplines.
  arXiv  Detail & Related papers  (2022-10-20T07:16:53Z)
• Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot [112.21008828205409]
  Comma.ai claims one $999 aftermarket device mounted with a single camera and board inside owns the ability to handle L2 scenarios. Together with open-sourced software of the entire system released by Comma.ai, the project is named Openpilot. In this report, we would like to share our latest findings, shed some light on the new perspective of end-to-end autonomous driving from an industrial product-level side.
  arXiv  Detail & Related papers  (2022-06-16T13:43:52Z)
• Data-Driven Aerospace Engineering: Reframing the Industry with Machine Learning [49.367020832638794]
  The aerospace industry is poised to capitalize on big data and machine learning. Recent trends will be explored in context of critical challenges in design, manufacturing, verification and services.
  arXiv  Detail & Related papers  (2020-08-24T22:40:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.