Mortar: Evolving Mechanics for Automatic Game Design

2025-12-31

arXiv.org

AI Summary

This work proposes a novel approach that integrates quality-diversity (QD) search with large language models (LLMs) to automatically evolve diverse and playable game mechanics, addressing the time-consuming and limited diversity of manual design. The system synthesizes complete games from evolved mechanics and evaluates their impact on player skill ranking, using skill consistency as the core metric. It combines QD optimization, LLM-based generation, game synthesis, and tree search in a unified framework. Experimental results demonstrate that the generated mechanics significantly improve skill differentiation among players. The effectiveness of each component is further validated through user studies and ablation analyses, confirming the synergy between QD-driven exploration and LLM-powered creativity in procedural game design.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Multiagent Systems: Mechanism Design
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

We present Mortar, a system for autonomously evolving game mechanics for automatic game design. Game mechanics define the rules and interactions that govern gameplay, and designing them manually is a time-consuming and expert-driven process. Mortar combines a quality-diversity algorithm with a large language model to explore a diverse set of mechanics, which are evaluated by synthesising complete games that incorporate both evolved mechanics and those drawn from an archive. The mechanics are evaluated by composing complete games through a tree search procedure, where the resulting games are evaluated by their ability to preserve a skill-based ordering over players -- that is, whether stronger players consistently outperform weaker ones. We assess the mechanics based on their contribution towards the skill-based ordering score in the game. We demonstrate that Mortar produces games that appear diverse and playable, and mechanics that contribute more towards the skill-based ordering score in the game. We perform ablation studies to assess the role of each system component and a user study to evaluate the games based on human feedback.

Problem

• automatic game design
• game mechanics
• skill-based ordering
• procedural content generation
• quality-diversity

Innovation

• quality-diversity algorithm
• large language model
• game mechanics evolution
• skill-based ordering
• automatic game design