Intelligent Design 4.0: Paradigm Evolution Toward the Agentic AI Era

TL;DR

This paper traces Intelligent Design (ID) from rule-based systems to autonomous, foundation-model-driven, multi-agent AI configurations, introducing ID 4.0 as an agentic paradigm for end-to-end engineering design. It presents a five-stage agent architecture aligned with Beitz's design process (RAA, CGA, EGA, DMA, DOA) and an ontological framework to coordinate data, agents, and problem formulations across the design lifecycle. The discussion highlights critical challenges in design data foundations, agent collaboration, and multi-scale problem formulations, proposing strategies such as open data, standardized schemas, negotiation protocols, and cross-domain integration to realize scalable, autonomous design. The work aims to catalyze advances in adaptive, autonomous, and efficient design processes capable of handling increasing engineering complexity.

Abstract

Research and practice in Intelligent Design (ID) have significantly enhanced engineering innovation, efficiency, quality, and productivity over recent decades, fundamentally reshaping how engineering designers think, behave, and interact with design processes. The recent emergence of Foundation Models (FMs), particularly Large Language Models (LLMs), has demonstrated general knowledge-based reasoning capabilities, and open new avenues for further transformation in engineering design. In this context, this paper introduces Intelligent Design 4.0 (ID 4.0) as an emerging paradigm empowered by foundation model-based agentic AI systems. We review the historical evolution of ID across four distinct stages: rule-based expert systems, task-specific machine learning models, large-scale foundation AI models, and the recent emerging paradigm of foundation model-based multi-agent collaboration. We propose an ontological framework for ID 4.0 and discuss its potential to support end-to-end automation of engineering design processes through coordinated, autonomous multi-agent-based systems. Furthermore, we discuss challenges and opportunities of ID 4.0, including perspectives on data foundations, agent collaboration mechanisms, and the formulation of design problems and objectives. In sum, these insights provide a foundation for advancing Intelligent Design toward greater adaptivity, autonomy, and effectiveness in addressing the growing complexity of engineering design.

Figures (7)

• Figure 1: The Four-stage Evolution of the Intelligent Design Paradigm
• Figure 2: Representative ID 1.0 Systems: (A) DANE Vattam2011, a design by analogy to nature engine; (B) INNOGPS Luo2021, a computer-aided system for design ideation and exploration
• Figure 3: Representative ID 2.0 Systems: (A) DL-based design stimuli search system that retrieves analogous visual designs Kwon2022; (B) DL-based linkage design generation system that synthesizes mechanical linkages Nobari2024
• Figure 4: Representative ID 3.0 Systems: (A) ZOO GregSweeneyZooCorporation2025, an LLM-based Text-to-CAD system; (B) AutoTRIZ Jiang2025autotriz, an artificial ideation system with TRIZ and LLMs
• Figure 5: The Framework of an Exemplar AI Agent