Code2Games：赋能编码智能体生成游戏世界
Code2Games: Enabling Coding Agents for Gaming World Generation
浏览论文内容
中文总结 AI 辅助
提出Code2Games智能体框架，基于Blender和虚幻引擎5，通过共享表示与执行引导重建，生成高质量游戏世界，并在GameCode4D基准上显著提升视觉与交互质量。
中文摘要 AI 辅助
从自然语言游戏意图生成高质量游戏世界，需要联合推理场景结构、空间布局、游戏目标、交互实体和可执行的游戏逻辑。现有的编码智能体可以生成单个资产、场景或脚本，但往往难以在这些组件之间保持一致性。我们提出Code2Games，一个智能体框架，它基于从相同游戏意图生成的Blender基础世界来构建结构化游戏世界。Code2Games通过共享的场景-游戏表示和持久的元素对应关系，协调场景分析、游戏规划、约束游戏世界生成和游戏引擎定制。在世界生成后，Code2Games将生成的世界适配到虚幻引擎5，并采用执行引导的重建过程，利用编译诊断、运行时反馈和游戏测试结果来解决引擎适配过程中出现的不一致问题。为了系统评估游戏世界生成，我们引入了GameCode4D基准，该基准包含十个固定游戏提示，涵盖不同级别的场景和游戏复杂度。我们从四个维度评估生成结果：视觉质量、交互保真度、多模态工件质量和可玩游戏质量。实验表明，与编码智能体直接生成游戏世界以及现有基线方法相比，Code2Games在生成游戏世界的视觉质量和交互保真度，以及引擎适配后所得游戏的质量方面均有持续提升。
英文摘要
Generating a high-quality gaming world from a natural-language game intent requires joint reasoning about scene structure, spatial layout, gameplay objectives, interactive entities, and executable gameplay logic. Existing coding agents can generate individual assets, scenes, or scripts, but often struggle to maintain consistency across these components. We propose Code2Games, an agentic framework that builds a structured gaming world upon a base Blender world generated from the same game intent. Code2Games coordinates scene analysis, gameplay planning, constrained gaming-world generation, and gaming-engine customization through a shared scene-gameplay representation with persistent element correspondence. After world generation, Code2Games adapts the generated world to Unreal Engine 5 and employs an execution-guided reconstruction process that uses compilation diagnostics, runtime feedback, and gameplay test results to resolve inconsistencies arising during engine adaptation. To systematically evaluate gaming-world generation, we introduce the GameCode4D benchmark, which comprises ten fixed game prompts spanning different levels of scene and gameplay complexity. We evaluate the generated results across four dimensions: visual quality, interactive fidelity, multimodal artifact quality, and playable-game quality. Experiments demonstrate that, compared with direct gaming-world generation by coding agents and existing baseline methods, Code2Games consistently improves the visual quality and interactive fidelity of generated gaming worlds, as well as the quality of the resulting games after engine adaptation.
发表机构
- La Trobe University（拉筹伯大学）
- Peking University（北京大学）
机构由 AI 辅助整理，请以论文原文为准。
