ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Search

TL;DR

ScriptDoctor leverages large language models and tree search to autonomously generate and test PuzzleScript puzzle games, demonstrating a step towards fully automated game design pipelines.

Contribution

It introduces a novel LLM-driven system that iteratively generates, tests, and refines PuzzleScript games with minimal human intervention.

Findings

Automated game generation and testing in PuzzleScript.

Effective use of compilation errors and play-testing for iterative refinement.

Potential for long-term autonomous game design workflows.

Abstract

There is much interest in using large pre-trained models in Automatic Game Design (AGD), whether via the generation of code, assets, or more abstract conceptualization of design ideas. But so far this interest largely stems from the ad hoc use of such generative models under persistent human supervision. Much work remains to show how these tools can be integrated into longer-time-horizon AGD pipelines, in which systems interface with game engines to test generated content autonomously. To this end, we introduce ScriptDoctor, a Large Language Model (LLM)-driven system for automatically generating and testing games in PuzzleScript, an expressive but highly constrained description language for turn-based puzzle games over 2D gridworlds. ScriptDoctor generates and tests game design ideas in an iterative loop, where human-authored examples are used to ground the system's output, compilation errors from the PuzzleScript engine are used to elicit functional code, and search-based agents play-test generated games. ScriptDoctor serves as a concrete example of the potential of automated, open-ended LLM-based workflows in generating novel game content.