DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914399334170624 |
|---|---|
| author | Pradas-Gomez, Alejandro Brahma, Arindam Isaksson, Ola |
| author_facet | Pradas-Gomez, Alejandro Brahma, Arindam Isaksson, Ola |
| contents | 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 10 repeated independent runs. The paper discusses the paradigm shift and the practical consequences of adopting agentic automation, including unintended effects on the nature of engineering work when removing mundane tasks and creating an exhausting supervisory role. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10249 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice Pradas-Gomez, Alejandro Brahma, Arindam Isaksson, Ola Software Engineering Artificial Intelligence Human-Computer Interaction 68T42, 68T05, 74-04, 68T35 I.2.11; I.2.1; J.6; H.1.2; I.2.6 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 10 repeated independent runs. The paper discusses the paradigm shift and the practical consequences of adopting agentic automation, including unintended effects on the nature of engineering work when removing mundane tasks and creating an exhausting supervisory role. |
| title | DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice |
| topic | Software Engineering Artificial Intelligence Human-Computer Interaction 68T42, 68T05, 74-04, 68T35 I.2.11; I.2.1; J.6; H.1.2; I.2.6 |
| url | https://arxiv.org/abs/2603.10249 |