Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering
This work addresses the bottleneck of capturing human complexity in simulations for researchers in social systems and AI, though it appears incremental as it builds on existing prompt engineering methods.
The research tackled the problem of accurately representing complex human-driven behavior in agent-based modeling by using large language models through prompt engineering, resulting in simulations of a two-agent negotiation and a six-agent murder mystery game as believable proxies.
The final frontier for simulation is the accurate representation of complex, real-world social systems. While agent-based modeling (ABM) seeks to study the behavior and interactions of agents within a larger system, it is unable to faithfully capture the full complexity of human-driven behavior. Large language models (LLMs), like ChatGPT, have emerged as a potential solution to this bottleneck by enabling researchers to explore human-driven interactions in previously unimaginable ways. Our research investigates simulations of human interactions using LLMs. Through prompt engineering, inspired by Park et al. (2023), we present two simulations of believable proxies of human behavior: a two-agent negotiation and a six-agent murder mystery game.