LLMs are the Ideal Candidate for Mixed-Initiative Game Design Pillar Workflows

2026-05-10

AI Summary

This study addresses the challenges of ambiguous core vision communication and inconsistent player experiences in game development by systematically integrating large language models (LLMs) into a design-pillar-driven, mixed-initiative development workflow. We introduce a formal definition of game design pillars and present SPINE, a prototype tool that leverages LLMs such as Gemini-2.0-Flash and GPT-4o-mini to support pillar creation and design decision-making. Evaluation through user studies, case deployments, and expert interviews demonstrates that Gemini exhibits superior performance in output diversity and consistency, while developers provided positive feedback on SPINE’s utility. These findings validate the feasibility and potential of LLMs in enabling design-pillar-centric game development.

Abstract

Game Design Pillars are natural language artifacts commonly used in game development to communicate a project's core vision and ensure a coherent player experience. Their linguistic nature aligns well with the strengths of Large Language Models (LLMs), which excel at generating and interpreting natural language, making them strong candidates for supporting mixed-initiative workflows centered on design pillars. In this study, we introduce a formal definition of game design pillars, present an initial prototype -- SPINE -- and investigate the utility of LLMs in the creation and decision-making processes associated with pillar-driven workflows. We begin with a pre-study to identify an appropriate model, comparing \texttt{gemini-2.0-flash} and \texttt{GPT-4o-mini}. Results show that Gemini is better suited to our tasks due to its greater output variety and consistency. We then conduct a case study by deploying the tool at a local game jam. Findings indicate positive reception and clear value in integrating SPINE into early-stage development. Finally, we interview four experts, demonstrating the tool and allowing them to experiment with it in a controlled environment. While individual perspectives vary, the overall perception is encouraging and supports our intuition: LLMs can meaningfully contribute to game design pillar workflows. These early findings highlight the potential of formalizing pillar-driven design as a research space and point toward several promising avenues for future work.

Problem

• Game Design Pillars
• Large Language Models
• Mixed-Initiative Workflows
• Game Development
• Natural Language Artifacts

Innovation

• Large Language Models
• Game Design Pillars
• Mixed-Initiative Workflow
• SPINE
• Generative AI in Game Design