Paper page - CreativeGame:Toward Mechanic-Aware Creative Game Generation

Source: https://huggingface.co/papers/2604.19926

Abstract

A multi-agent system for iterative HTML5 game generation that uses programmatic rewards, lineage memory, runtime validation, and mechanic-guided planning to enable interpretable version-to-version evolution.

Large language modelscan 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. This report presents CreativeGame, amulti-agent systemfor iterativeHTML5 game generationthat addresses these issues through four coupled ideas: aproxy rewardcentered onprogrammatic signalsrather than pure LLM judgment;lineage-scoped memoryfor cross-version experience accumulation;runtime validationintegrated into both repair and reward; and amechanic-guided planningloop 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 interpretableversion-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.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2604\.19926

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2604.19926 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2604.19926 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2604.19926 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.