LLMs and ABMs

In a previous post we talked about the potential of Generative AI for urban modeling, keeping with this theme at the 11th International Conference on Computational Social Science (IC2S2), Na Jiang, Boyu Wang and myself had a poster entitled  Agent-based Models with Large Language Models: Two Modeling Examples. 

In this poster and extended abstract we detail how LLMs can help with many aspects of agent-based modeling development. If this sounds of interest, below you can see the abstract, the poster and the full referece and link to the extended abstract .

Abstract:

Large language models (LLMs) play an important role in AI-powered code assistants such as code completion, debugging, and documentation. Such models can be further fine-tuned on smaller amount of data for specific tasks, often with the improvement of performance compared to generic LLMs. However, such fine-tuning techniques are seldomly used in generating sophisticated agent-based models (ABMs), because they are often implemented as software that demands extra standards such as the Overview, Design concepts, and Details (ODD) protocol. This research examines how we can bridge this gap by utilizing LLMs in designing or conceptualizing, building, and running agent-based models in the form of user prompts. In this work, two models are created to demonstrate the proposed method. Specifically, Sakoda's checkerboard model of social interaction is created by LLM from explicit design and description through prompts. The other model stimulates consumer preferences and restaurant visits as designed and implemented by a LLM. These models are evaluated by human experts on their code correctness and quality for both verification and validation purposes. This work serves as a first step towards fine-tuned LLMs on existing models and documentations to create high-quality and functional ABMs based on either user prompts or standard protocols, contributing to further exploration on the future of AI-assisted geospatial simulation development.

Keywords: agent-based modeling, geospatial simulations, large language models, generative AI, coding 

Full reference: 

Jiang, N., Wang, B. and Crooks, A.T. (2025), Agent-based Models with Large Language Models: Two Modeling Examples, 11th International Conference on Computational Social Science (IC2S2), 21-24th July, Norrkoping, Sweden. (extended abstract pdf) (poster pdf)

New Editorial: Generative AI and Urban Modeling

In the current issue of Environment and Planning B, we (Boyu Wang, Na Jiang and myself) have a new editorial entitled "Generative AI and Urban Modeling". The premise of this editorial is that Generative AI (GenAI) is impacting all aspects of our daily lives and as such has we were wondering how will it impact urban modeling? 

For example, in the editorial we discuss how  GenAI could speed up the overall urban modeling process. To demonstrate this we show how ChatGPT (and its built-in coding interface Canvas) can take published papers and build agent-based models from them (one being of an abstract space and another being spatially explicit). 

However, while model building is time consuming task, another challenge modelers face is how to incorporate decision making within them. To this end we also discuss how large language models (LLMs) have the potential to help with  agent-decision making in the form of generating  agent-personas or scheduling agent activities. 

We conclude the editorial with a series of questions: how will GenAI impact urban modeling? Will it open up the field to more people without the need for strong coding skills? Will we see growth in using LLMs for generating behavior? Will GenAI lead to a new generation of modeling toolkits? While these are only a short list of questions, they also raise concerns that relate back to some of the more thorny issues of urban modeling, that of verification and validation. 

If this sounds of interest you can read the full editorial here. 

Full Referece: 

Crooks, A.T., Jiang, N. and Wang, B. (2025), Generative AI and Urban Modeling, Environment and Planning B, 52(6), 1277-1281. (pdf)