DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice

2026-03-10

AI Summary

Traditional engineering analysis automation relies on fixed workflows and rigid interfaces, making it ill-suited to accommodate changes in data formats, units, or methodologies driven by product evolution. This work proposes DUCTILE, a novel framework that introduces large language model (LLM) agents into engineering analysis automation for the first time. By decoupling adaptive task orchestration from deterministic tool execution, DUCTILE dynamically interprets design documentation and adjusts processing pipelines under engineer supervision. The approach ensures both regulatory compliance and robustness while supporting structured document parsing, seamless tool integration, and human oversight. Evaluated on structural analysis tasks in aerospace manufacturing, DUCTILE successfully handled input variations, consistently producing results meeting expert standards across multiple independent runs and demonstrating practical viability through deployment by frontline engineers.

Technology Category

• Natural Language Processing: Prompt Engineering / Prompting
• Machine Learning: Evaluation and Analysis
• Humans and AI: Planning and Decision Support for Human-Machine Teams

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

Engineering analysis automation in product development relies on rigid interfaces between tools, data formats and documented processes. When these interfaces change, as they routinely do as the product evolves in the engineering ecosystem, the automation support breaks. This paper presents a DUCTILE (Delegated, User-supervised Coordination of Tool- and document-Integrated LLM-Enabled) agentic orchestration, an approach for developing, executing and evaluating LLM-based agentic automation support of engineering analysis tasks. The approach separates adaptive orchestration, performed by the LLM agent, from deterministic execution, performed by verified engineering tools. The agent interprets documented design practices, inspects input data and adapts the processing path, while the engineer supervises and exercises final judgment. DUCTILE is demonstrated on an industrial structural analysis task at an aerospace manufacturer, where the agent handled input deviations in format, units, naming conventions and methodology that would break traditional scripted pipelines. Evaluation against expert-defined acceptance criteria and deployment with practicing engineers confirm that the approach produces correct, methodologically compliant results across repeated independent runs. The paper discusses practical consequences of adopting agentic automation, including unintended effects on the nature of engineering work and the tension between removing mundane tasks and creating an exhausting supervisory role.

Problem

• engineering analysis automation
• rigid interfaces
• product development
• automation breakdown
• interface evolution

Innovation

• Agentic LLM
• Engineering Automation
• Adaptive Orchestration
• Human-in-the-loop
• Structural Analysis