Prompt Engineering Guidance for Conceptual Agent-based Model Extraction using Large Language Models

TL;DR

This paper provides detailed prompt engineering guidance for using large language models to extract and convert conceptual agent-based models into machine-readable formats like JSON, facilitating automation and manual understanding.

Contribution

It introduces a structured approach to prompt design for LLMs to improve extraction of agent-based models from conceptual descriptions, advancing automation in ABM development.

Findings

Effective prompts enable accurate extraction of ABM components

JSON format facilitates both human understanding and auto-code generation

Guidelines improve LLM performance in model extraction tasks

Abstract

This document contains detailed information about the prompts used in the experimental process discussed in the paper "Toward Automating Agent-based Model Generation: A Benchmark for Model Extraction using Question-Answering Techniques". The paper aims to utilize Question-answering (QA) models to extract the necessary information to implement Agent-based Modeling (ABM) from conceptual models. It presents the extracted information in formats that can be read by both humans and computers (i.e., JavaScript Object Notation (JSON)), enabling manual use by humans and auto-code generation by Large Language Models (LLM).