Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering

Edward Junprung
8/14/2023
cs.AIcs.MA

No official code found. Best implementation: ejunprung/llm-agents (18 stars, last commit 2023-08-05).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

ejunprung/llm-agentsCommunity100%

Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering

184Jupyter NotebookAug 4, 20233 years ago

Similar Papers

LLM-Augmented Agent-Based Modelling for Social Simulations: Challenges and Opportunities

90% match2024

Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordia

89% match1 repo1.5k2023

Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles

89% match2025

Integrating LLM in Agent-Based Social Simulation: Opportunities and Challenges

89% match2025

Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives

88% match2023

Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations

88% match1 repo372023

Cite this paper

@article{junprung2023exploring,
  title  = {Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering},
  author = {Edward Junprung},
  year   = {2023},
  eprint = {2308.07411},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.07411v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.07411.svg)](https://codeofpaper.com/paper/2308.07411)

Discussion