Problem
Research questions and friction points this paper is trying to address.
engineering workflows
agentic AI
automotive engineering
sequential decision processes
model-based systems engineering
Automotive Engineering-Centric Agentic AI Workflow Framework
🤖 AI Summary
This work addresses the limitations of traditional AI approaches, which reduce engineering activities to isolated tasks and struggle to handle the iterative nature, constraints, and historical dependencies inherent in complex engineering workflows. To overcome these challenges, the paper introduces the Agentic Engineering Intelligence (AEI) framework, which reconceptualizes engineering AI as a process-level intelligence problem. By integrating a control-theoretic perspective, AEI unifies the modeling of objectives, AI agents, and toolchain feedback into a sequential decision-making system capable of historical awareness and constraint satisfaction. The framework synergistically combines AI agents, toolchain integration, state estimation, retrieval-augmented decision-making, and multimodal knowledge reuse. Its generality and feasibility are demonstrated across diverse automotive engineering scenarios—including suspension design, reinforcement learning hyperparameter tuning, aerodynamic exploration, and Model-Based Systems Engineering—providing an empirical roadmap toward industrial-scale collaborative intelligence.
📝 Abstract
Engineering workflows such as design optimization, simulation-based diagnosis, control tuning, and model-based systems engineering (MBSE) are iterative, constraint-driven, and shaped by prior decisions. Yet many AI methods still treat these activities as isolated tasks rather than as parts of a broader workflow. This paper presents Agentic Engineering Intelligence (AEI), an industrial vision framework that models engineering workflows as constrained, history-aware sequential decision processes in which AI agents support engineer-supervised interventions over engineering toolchains. 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. A control-theoretic interpretation is also possible, in which engineering objectives act as reference signals, agents act as workflow controllers, and toolchains provide feedback for intervention selection. Representative automotive use cases in suspension design, reinforcement learning tuning, multimodal engineering knowledge reuse, aerodynamic exploration, and MBSE show how diverse workflows can be expressed within a common formulation. Overall, the paper positions engineering AI as a problem of process-level intelligence and outlines a practical roadmap for future empirical validation in industrial settings.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Agentic AI
Engineering Workflow
Sequential Decision Process
Model-Based Systems Engineering
Control-Theoretic AI
🔎 Similar Papers
No similar papers found.
