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

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

URL: http://arxiv.org/abs/2603.10249v2
Date: Tue, 17 Mar 2026 02:22:06 GMT
Title: DUCTILE: Agentic LLM Orchestration of Engineering Analysis in Product Development Practice
Abstract summary: Engineering analysis automation in product development relies on rigid interfaces between tools, data formats and documented processes.<n>This paper presents a DUCTILE (Delegated, User-supervised Coordination of Tool- and document-Integrated LLM-Enabled) agentic orchestration.<n>The agent interprets documented design practices, inspects input data and adapts the processing path, while the engineer supervises and exercises final judgment.
Score: 41.99844472131922
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
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 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.

Related papers

AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems [82.01232437066487]
AgentX is a production-deployed multi-agent system that restructures this production function.<n>It autonomously generates, implements, evaluates, and learns from recommendation experiments.<n>AgentX orchestrates four tightly coupled stages in a closed loop.
arXiv Detail & Related papers (2026-06-25T10:42:28Z)
Collaborative Agent Reasoning Engineering (CARE): A Three-Party Design Methodology for Systematically Engineering AI Agents with Subject Matter Experts, Developers, and Helper Agents [0.16302332606018002]
Collaborative Agent Reasoning Engineering (CARE) is a disciplined methodology for engineering Large Language Model (LLM) agents in scientific domains.<n>CARE specifies behavior, grounding, tool orchestration, and verification through reusable artifacts and systematic, stage-gated phases.
arXiv Detail & Related papers (2026-04-30T15:54:47Z)
Automotive Engineering-Centric Agentic AI Workflow Framework [8.940446431523911]
This paper presents Agentic Engineering Intelligence (AEI), an industrial vision framework that models engineering as constrained, history-aware sequential decision processes.<n>AEI links an offline phase for engineering data processing and workflow-memory construction with an online phase for workflow-state estimation, retrieval, and decision support.
arXiv Detail & Related papers (2026-04-09T04:22:18Z)
kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation [0.5833117322405447]
We introduce kRAIG, an AI agent that translates natural language specifications into production-ready KubeReason Pipelines (KFP)<n>To resolve ambiguity in user intent, we propose ReQuesAct, an interaction framework that explicitly clarifies intent prior to pipeline synthesis.<n>Our framework achieves a 3x improvement in extraction and loading success and a 25 percent increase in transformation accuracy compared to state-of-the-art agentic baselines.
arXiv Detail & Related papers (2026-03-19T17:53:00Z)
AI Agent for Reverse-Engineering Legacy Finite-Difference Code and Translating to Devito [0.0]
This study develops an integrated AI framework to facilitate the transformation of legacy finite difference implementations into the Devito environment.<n>Retrieval-Augmented Generation (RAG) and open-source Large Language Models are combined through multi-stage iterative in the system's hybrid LangGraph architecture.
arXiv Detail & Related papers (2026-01-26T11:31:00Z)
A Practical Guide for Designing, Developing, and Deploying Production-Grade Agentic AI Workflows [4.3073750462661256]
Agentic AI marks a major shift in how autonomous systems reason, plan, and execute multi-step tasks.<n>This paper provides a practical, end-to-end guide for designing, developing, and deploying production-quality agentic AI systems.
arXiv Detail & Related papers (2025-12-09T16:23:05Z)
Logic Mining from Process Logs: Towards Automated Specification and Verification [0.0]
This article presents an approach for generating logical specifications from process models discovered via workflow.<n>The study examines the impact of quality data, particularly noise, on the structure and testability of generated specifications.
arXiv Detail & Related papers (2025-06-10T09:44:19Z)
APE-Bench I: Towards File-level Automated Proof Engineering of Formal Math Libraries [5.227446378450704]
APE-Bench I is the first realistic benchmark built from real-world commit histories of Mathlib4.<n>Eleanstic is a scalable parallel verification infrastructure optimized for proof checking across multiple versions of Mathlib.
arXiv Detail & Related papers (2025-04-27T05:04:02Z)
The Foundations of Computational Management: A Systematic Approach to Task Automation for the Integration of Artificial Intelligence into Existing Workflows [55.2480439325792]
This article introduces Computational Management, a systematic approach to task automation. The article offers three easy step-by-step procedures to begin the process of implementing AI within a workflow.
arXiv Detail & Related papers (2024-02-07T01:45:14Z)
TaskBench: Benchmarking Large Language Models for Task Automation [82.2932794189585]
We introduce TaskBench, a framework to evaluate the capability of large language models (LLMs) in task automation. Specifically, task decomposition, tool selection, and parameter prediction are assessed. Our approach combines automated construction with rigorous human verification, ensuring high consistency with human evaluation.
arXiv Detail & Related papers (2023-11-30T18:02:44Z)
ProAgent: From Robotic Process Automation to Agentic Process Automation [87.0555252338361]
Large Language Models (LLMs) have emerged human-like intelligence. This paper introduces Agentic Process Automation (APA), a groundbreaking automation paradigm using LLM-based agents for advanced automation. We then instantiate ProAgent, an agent designed to craft from human instructions and make intricate decisions by coordinating specialized agents.
arXiv Detail & Related papers (2023-11-02T14:32:16Z)
Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelines [48.7576911714538]
The proposed approach is aimed to automate the design of composite machine learning pipelines. It designs the pipelines with a customizable graph-based structure, analyzes the obtained results, and reproduces them. The software implementation on this approach is presented as an open-source framework.
arXiv Detail & Related papers (2021-06-26T23:19:06Z)

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