Generalist Generative Agent: Open-ended design exploration with large language models


METADATA ONLY
Loading...

Date

2025

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Architects often navigate ambiguity in early-stage design by using metaphors and conceptual models to transform abstract ideas into architectural forms. However, current computational tools struggle with such exploratory processes due to narrowly defined design spaces. This paper investigates whether Large Language Models (LLMs) can offer an alternative generative paradigm by interpreting human intent and translating it into actionable design logic. We propose an Agentic AI framework in which LLM agents interpret metaphors, formulate design tasks, and generate procedural 3D models. Using this framework, we produced 1,000 procedural designs and 4,000 images based on 20 metaphors to demonstrate the emergent capabilities of LLMs for creating architecturally relevant conceptual models. Our findings suggest that LLMs effectively engage with ambiguity, delivering diverse, meaningful outputs with notable potential for early phase design. We discuss the strengths and shortcomings of the AI agents within the framework and suggest ways to extend their capacity for tackling open-ended design challenges, thereby enhancing their relevance in architectural practice.

Publication status

published

Book title

Architectural Informatics: Proceedings of the 30th International Conference of the Association for Computer-Aided Architectural Design Research in Asia (CAADRIA 2025), Volume 2

Journal / series

Volume

1

Pages / Article No.

193 - 202

Publisher

Association for Computer-Aided Architectural Design Research in Asia

Event

30th International Conference on Computer-Aided Architectural Design Research in Asia (CAADRIA 2025)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Agentic AI; Large language models; Generative architectural design; Multi-agent framework; Design synthesis

Organisational unit

09566 - Dillenburger, Benjamin / Dillenburger, Benjamin

Notes

Funding

Related publications and datasets