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

2024-05-12

Journal of Artificial Societies and Social Simulation

AI Summary

Agent-based social simulation (ABSS) modeling traditionally relies heavily on domain expertise, suffers from lengthy development cycles, and imposes high conceptualization barriers. Method: This paper pioneers the integration of conversational AI systems (CAIS)—such as ChatGPT—into the ABSS modeling workflow. We propose a structured prompt engineering methodology tailored to engineering-oriented ABSS frameworks, enabling the construction of reusable prompt scripts that bridge the methodological gap between CAIS and ABSS, thereby facilitating rapid conceptual modeling with minimal prior domain knowledge. Contribution/Results: Evaluated in a museum adaptive architecture case study, our approach successfully generated a complete ABSS conceptual model, empirically validating CAIS as an effective modeling collaborator. It significantly reduces model design time and establishes a novel paradigm for agile ABSS development and cross-disciplinary collaboration.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Agentic search

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. While scepticism towards anything new is inherent to human nature, we firmly believe it is imperative to initiate the use of this innovative technology to support ABSS model design. This paper presents a proof-of-concept that demonstrates how 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 ABSS models with or by the CAIS. The effectiveness of the script is demonstrated through an illustrative case study concerning the use of adaptive architecture in museums. Despite occasional inaccuracies and divergences in conversation, the CAIS proved to be a valuable companion for ABSS modellers.

Problem

• Exploring conversational AI's potential for agent-based social simulation design
• Developing conceptual ABSS models rapidly with minimal prior knowledge
• Creating prompt scripts to enable AI-assisted social simulation modeling

Innovation

• Used conversational AI systems for social simulation design
• Employed advanced prompt engineering techniques
• Applied Engineering ABSS framework for model creation