LLM2FEA: Discover Novel Designs with Generative Evolutionary Multitasking

2024-06-21

arXiv.org

AI Summary

This work addresses the challenge of generating 3D aerodynamic structures that are both innovative and physically feasible for scientific and engineering applications. Method: We propose a generative design framework synergistically integrating large language models (LLMs) and multifactorial evolutionary algorithms (MFEAs). The LLM performs knowledge transfer to generate high-quality textual prompts that guide generative modeling, while the MFEA concurrently optimizes structural novelty, aerodynamic performance, and engineering constraints within a multitask setting. Contribution/Results: To our knowledge, this is the first work to deeply integrate MFEA with LLMs for cross-domain implicit knowledge transfer and co-optimization—eliminating biases inherent in manual prompt engineering. Evaluated on 3D aerodynamic design tasks, our method successfully produces multiple viable designs satisfying real-world physical constraints, demonstrating significant structural novelty and functional utility. Experimental results validate the framework’s effectiveness and scalability for creative engineering discovery.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Generation
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The rapid research and development of generative artificial intelligence has enabled the generation of high-quality images, text, and 3D models from text prompts. This advancement impels an inquiry into whether these models can be leveraged to create digital artifacts for both creative and engineering applications. Drawing on innovative designs from other domains may be one answer to this question, much like the historical practice of ``bionics", where humans have sought inspiration from nature's exemplary designs. This raises the intriguing possibility of using generative models to simultaneously tackle design tasks across multiple domains, facilitating cross-domain learning and resulting in a series of innovative design solutions. In this paper, we propose LLM2FEA as the first attempt to discover novel designs in generative models by transferring knowledge across multiple domains. By utilizing a multi-factorial evolutionary algorithm (MFEA) to drive a large language model, LLM2FEA integrates knowledge from various fields to generate prompts that guide the generative model in discovering novel and practical objects. Experimental results in the context of 3D aerodynamic design verify the discovery capabilities of the proposed LLM2FEA. The designs generated by LLM2FEA not only satisfy practicality requirements to a certain degree but also feature novel and aesthetically pleasing shapes, demonstrating the potential applications of LLM2FEA in discovery tasks.

Problem

• Develops AI designer for innovative cross-domain object creation
• Ensures generated objects meet real-world physical specifications
• Improves design diversity and functionality over existing models

Innovation

• LLM-driven MultiTask Evolutionary Algorithm (LLM2TEA)
• Text-to-3D generative model produces phenotypes
• Physics simulation model assesses physical properties