LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents

TL;DR

This paper investigates using Large Language Models as automated testers to measure game difficulty, demonstrating their potential to correlate with human perceptions and aid game development.

Contribution

The study introduces a novel framework employing LLMs for game difficulty assessment and validates its effectiveness on popular strategy games.

Findings

LLMs' performance correlates with human difficulty ratings.

Simple prompting guides LLMs to effectively assess game challenge.

LLMs can serve as reliable tools in game testing processes.

Abstract

Recent advances in Large Language Models (LLMs) have demonstrated their potential as autonomous agents across various tasks. One emerging application is the use of LLMs in playing games. In this work, we explore a practical problem for the gaming industry: Can LLMs be used to measure game difficulty? We propose a general game-testing framework using LLM agents and test it on two widely played strategy games: Wordle and Slay the Spire. Our results reveal an interesting finding: although LLMs may not perform as well as the average human player, their performance, when guided by simple, generic prompting techniques, shows a statistically significant and strong correlation with difficulty indicated by human players. This suggests that LLMs could serve as effective agents for measuring game difficulty during the development process. Based on our experiments, we also outline general principles and guidelines for incorporating LLMs into the game testing process.