Julian Togelius | Andrea De Lorenzo

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

Fri, 06 Jun 2025 00:00:00 +0000

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.

God's Innovation Project - Empowering The Player With Generative AI

Mon, 31 Mar 2025 00:00:00 +0000

In this paper, we present God’’s Innovation Project (GIP), a god game where players collect words to dynamically terraform the landscape using generative AI. A god game is a genre where players take on the role of a deity, indirectly influencing Non-Player Characters (NPCs) to perform various tasks. These games typically grant players supernatural abilities, such as terrain manipulation or weather control. Traditional god games rely on predefined environments and mechanics, typically created by a human designer. In contrast, GIP allows players to shape the game world procedurally through text-based input. Using a lightweight generative AI model, we create a gamified pipeline which transforms the player’’s text prompts into playable game terrain in real time. To evaluate the impact of this AI-driven mechanic, we conduct a user study analyzing how players interacted with and experienced the system. Our findings provide insights into player engagement, the effectiveness of AI-generated terrain, and the role of

Large Language Models and Games: A Survey and Roadmap

Wed, 28 Feb 2024 00:00:00 +0000

Recent years have seen an explosive increase in research on large language models (LLMs), and accompanying public engagement on the topic. While starting as a niche area within natural language processing, LLMs have shown remarkable potential across a broad range of applications and domains, including games. This paper surveys the current state of the art across the various applications of LLMs in and for games, and identifies the different roles LLMs can take within a game. Importantly, we discuss underexplored areas and promising directions for future uses of LLMs in games and we reconcile the potential and limitations of LLMs within the games domain. As the first comprehensive survey and roadmap at the intersection of LLMs and games, we are hopeful that this paper will serve as the basis for groundbreaking research and innovation in this exciting new field.