CreativeGame: Toward Mechanic-Aware Creative Game Generation
Summary: arXiv:2604.19926v1 Announce Type: new
Abstract: Large language models can generate plausible game code, but turning this capability into iterative creative improvement remains difficult. In practice, single-shot generation often produces brittle runtime behavior, weak accumulation of experience across versions, and creativity scores that are too subjective to serve as reliable optimization signals. A further limitation is that mechanics are frequently treated only as post-hoc descriptions, rather than as explicit objects that can be planned, tracked, preserved, and evaluated during generation.
Introduction to CreativeGame
This report presents CreativeGame, a multi-agent system for iterative HTML5 game generation that addresses these issues through four coupled ideas:
- A proxy reward centered on programmatic signals rather than pure LLM judgment.
- Lineage-scoped memory for cross-version experience accumulation.
- Runtime validation integrated into both repair and reward.
- A mechanic-guided planning loop in which retrieved mechanic knowledge is converted into an explicit mechanic plan before code generation begins.
Goals and Objectives
The goal of CreativeGame is not merely to produce a playable artifact in one step, but to support interpretable version-to-version evolution. This approach allows developers and researchers to observe how game mechanics can evolve and improve over successive iterations.
System Overview
The current system contains:
- 71 stored lineages
- 88 saved nodes
- A 774-entry global mechanic archive
Implemented in a total of 6,181 lines of Python, CreativeGame is substantial enough to support architectural analysis, reward inspection, and real lineage-level case studies rather than only prompt-level demos.
Mechanic-Level Innovation
A real four-generation lineage demonstrates that mechanic-level innovation can emerge in later versions. This innovation can be inspected directly through version-to-version records, allowing for a deeper understanding of how changes in mechanics can impact gameplay.
Contributions to Game Development
The central contribution of CreativeGame is not only in game generation but also in providing a concrete pipeline for observing progressive evolution through explicit mechanic change. The insights gained from this system can inform future game development practices and enhance the understanding of game mechanics in a way that is systematic and replicable.
Conclusion
CreativeGame represents a significant advancement in the field of automated game generation. By focusing on mechanic awareness and iterative improvement, this system provides a framework for creating games that are not only playable but also evolving and increasingly complex. As the gaming landscape continues to evolve, tools like CreativeGame could play a pivotal role in shaping the future of game development.