Procedurally generating rules to adapt difficulty for narrative puzzle games

TL;DR

This paper presents a method combining genetic algorithms and large language models to procedurally generate and communicate rules that adapt the difficulty of narrative puzzle games for educational purposes, especially for young children.

Contribution

It introduces a novel approach that uses genetic algorithms and language models to generate and explain game rules, enabling difficulty adaptation in educational narrative puzzles.

Findings

The approach can approximate target difficulty within 24 generations.

The method successfully integrates rule generation with narrative communication.

Initial tests show potential for adaptive educational game design.

Abstract

This paper focuses on procedurally generating rules and communicating them to players to adjust the difficulty. This is part of a larger project to collect and adapt games in educational games for young children using a digital puzzle game designed for kindergarten. A genetic algorithm is used together with a difficulty measure to find a target number of solution sets and a large language model is used to communicate the rules in a narrative context. During testing the approach was able to find rules that approximate any given target difficulty within two dozen generations on average. The approach was combined with a large language model to create a narrative puzzle game where players have to host a dinner for animals that can't get along. Future experiments will try to improve evaluation, specialize the language model on children's literature, and collect multi-modal data from players to guide adaptation.