Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.19926 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910156634193920 |
|---|---|
| author | Ma, Hongnan Wang, Han Wang, Shenglin Yin, Tieyue Shi, Yiwei Huang, Yucong Zou, Yingtian Wen, Muning Yang, Mengyue |
| author_facet | Ma, Hongnan Wang, Han Wang, Shenglin Yin, Tieyue Shi, Yiwei Huang, Yucong Zou, Yingtian Wen, Muning Yang, Mengyue |
| contents | Large language models can generate plausible game code, but turning this capability into \emph{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.
This report presents \textbf{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; and a mechanic-guided planning loop in which retrieved mechanic knowledge is converted into an explicit mechanic plan before code generation begins. The goal is not merely to produce a playable artifact in one step, but to support interpretable version-to-version evolution.
The current system contains 71 stored lineages, 88 saved nodes, and a 774-entry global mechanic archive, implemented in 6{,}181 lines of Python together with inspection and visualization tooling. The system is therefore substantial enough to support architectural analysis, reward inspection, and real lineage-level case studies rather than only prompt-level demos.
A real 4-generation lineage shows that mechanic-level innovation can emerge in later versions and can be inspected directly through version-to-version records. The central contribution is therefore not only game generation, but a concrete pipeline for observing progressive evolution through explicit mechanic change. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19926 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CreativeGame:Toward Mechanic-Aware Creative Game Generation Ma, Hongnan Wang, Han Wang, Shenglin Yin, Tieyue Shi, Yiwei Huang, Yucong Zou, Yingtian Wen, Muning Yang, Mengyue Artificial Intelligence Large language models can generate plausible game code, but turning this capability into \emph{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. This report presents \textbf{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; and a mechanic-guided planning loop in which retrieved mechanic knowledge is converted into an explicit mechanic plan before code generation begins. The goal is not merely to produce a playable artifact in one step, but to support interpretable version-to-version evolution. The current system contains 71 stored lineages, 88 saved nodes, and a 774-entry global mechanic archive, implemented in 6{,}181 lines of Python together with inspection and visualization tooling. The system is therefore substantial enough to support architectural analysis, reward inspection, and real lineage-level case studies rather than only prompt-level demos. A real 4-generation lineage shows that mechanic-level innovation can emerge in later versions and can be inspected directly through version-to-version records. The central contribution is therefore not only game generation, but a concrete pipeline for observing progressive evolution through explicit mechanic change. |
| title | CreativeGame:Toward Mechanic-Aware Creative Game Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.19926 |