Exploring the Potential of Conversational AI Support for Agent-Based Social Simulation Model Design - Paper

Oct 26, 2026

Upload by Fahsai

ChatGPT and other Conversational AI Systems (CAISs) are widely used, yet their role in Social Simulation research remains limited, with no clear evidence of application to Agent-Based Social Simulation (ABSS) model design. This paper presents an initial exploration showing how CAISs can support rapid, minimally knowledge-dependent development of innovative conceptual ABSS models. Using advanced prompt engineering and the Engineering ABSS (EABSS) framework, a reusable prompt script enables CAIS-assisted design, validated through a museum case study on adaptive architecture.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages25

Reading Time1 h 3 min

AccessFree to download

Motivation

Developing conceptual ABSS models with stakeholders

Improving EABSS usability and adding chatbot support

Two CAIS opportunities in this paper

Study timeframe and proposed approach

Exploring the Potential of Conversational AI Support for Agent-Based Social Simulation Model Design Peer-Olaf Siebers1 1 Intelligent Modelling and Analysis Research Group, School of Computer Science, University of Nottingham, Nottingham, NG8 1BB, United Kingdom Correspondence should [be addressed to](be addressed to peer-olaf.siebers@nottingham.ac.uk)[ peer-olaf.siebers@nottingham.ac.uk](be addressed to peer-olaf.siebers@nottingham.ac.uk) Journal of Artificial Societies and Social Simulation 28(3) 2, 2025 Doi: 10.18564/jasss.5681 Url: [http://jasss.soc.surrey.ac.uk/28/3/2.html](http://jasss.soc.surrey.ac.uk/28/3/2.html) Received: 13-05-2024 Accepted: 08-04-2025 Published: 30-06-2025 Abstract: ChatGPT, the AI-powered chatbot with a massive user base of hundreds of millions, has become a global phenomenon. However, the use of Conversational AI Systems (CAISs) like ChatGPT for research in the field of Social Simulation is still limited. Specifically, there is no evidence of its usage in Agent-Based Social Simulation (ABSS) model design. This paper takes a crucial first step toward exploring the untapped potential of this emerging technology in the context of ABSS model design. The research presented here demonstrateshow CAISs can facilitate the development of innovative conceptual ABSS models in a concise timeframe and with minimal required upfront case-based knowledge. By employing advanced prompt engineering techniques and adhering to the Engineering ABSS framework, we have constructed a comprehensive prompt script that enables the design of conceptual ABSS models with or by the CAIS. A proof-of-concept application of the prompt script, used to generate the conceptual ABSS model for a case study on the impact of adaptive architecture in a museum environment, illustrates the practicality of the approach. Despite occasional inaccuracies and conversational divergence, the CAIS proved to be a valuable companion for ABSS modellers. Keywords: Agent-Based Modelling, Social Simulation, Conceptual Modelling, ChatGPT, Large Language Models, Prompt Engineering Motivation 1.1 Developing innovative conceptual Agent-Based Social Simulation (ABSS) models with the involvement of relevant key stakeholders can be challenging. In response to this challenge, we created the Engineering AgentBased Social Simulation (EABSS) framework some years ago, which supports the process of co-creating conceptualABSS models in a structured and standardised manner, involving all relevant key stakeholders (Siebers & Klügl 2017) . Despite our belief in the value of this resource for the social simulation community, its adoption has not met our expectations. Feedback gathered through discussions at conferences with community members pointed to several usability challenges that have limited broader engagement with the framework. These include a steep learning curve associated with effectively using the framework, the demanding role of the focus group moderator, and difficulties in gathering all necessary stakeholders for the process. 1.2 To address these concerns, our ongoing research efforts are directed at improving the usability of the EABSS framework, which we approach from two different angles. We are working on an Iteration and Information ReUse Schema that guides the EABSS framework user on how to reuse information gathered in the previous steps when initiating the next step. This should ease the pressure put on the moderator when moving to the next step defined in the framework. Additionally, we are exploring the option of providing support to users through the use of chatbots that possess the ability to comprehend and generate text resembling human language. With JASSS, 28(3) 2, 2025 [http://jasss.soc.surrey.ac.uk/28/3/2.html](http://jasss.soc.surrey.ac.uk/28/3/2.html) Doi: 10.18564/jasss.5681 the recent advancement of Conversational AI Systems (CAISs), there are numerous opportunities to assist the EABSS framework user throughout

FAQs

What gap does the paper identify in using Conversational AI for social simulation research?

It notes that evidence of CAIS usage specifically for Agent-Based Social Simulation (ABSS) model design is still lacking.

How does the proposed approach support ABSS conceptual model development?

It combines advanced prompt engineering with the EABSS framework, using a comprehensive prompt script to generate conceptual ABSS models with or by a CAIS.

What was the proof-of-concept application used to demonstrate practicality?

The prompt script generated a conceptual ABSS model for a case study on the impact of adaptive architecture in a museum environment.

Oct 26, 2026

Upload by Fahsai