arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.14724cs.AI
收藏

GameUIAgent:一种基于大语言模型的自动化游戏UI设计框架,采用结构化中间表示

GameUIAgent: An LLM-Powered Framework for Automated Game UI Design with Structured Intermediate Representation

Wei Zeng, Fengwei An, Zhen Liu, Jian Zhao

AI总结:

本文提出GameUIAgent框架,通过结构化中间表示将自然语言描述转化为Figma设计,结合神经符号管道实现迭代自校正,发现质量天花板效应和渲染评估保真原则。

摘要:

游戏UI设计需要在稀有度层级间保持一致的视觉资产,但这一过程仍主要依赖手动操作。我们提出了GameUIAgent,一种基于大语言模型的代理框架,通过设计规格JSON中间表示将自然语言描述转化为可编辑的Figma设计。一个六阶段的神经符号管道结合了大语言模型生成、确定性后处理和由视觉语言模型(VLM)引导的反射控制器(RC),实现迭代自校正,确保非退化的质量。在110个测试用例、三个大语言模型和三个UI模板上评估,跨模型分析建立了游戏领域的失败分类学(稀有度依赖的退化;视觉空缺)并揭示了两个关键经验发现。质量天花板效应(皮尔逊r=-0.96,p<0.01)表明RC改进受质量阈值以下的余量限制——这是视觉领域对应于测试时计算扩展定律的 counterpart。渲染-评估保真原则揭示了部分渲染增强 paradoxically 会通过放大结构性缺陷而降低VLM评估。这些结果为LLM驱动的视觉生成代理在游戏生产中的奠定了基础原理。

英文摘要:

Game UI design requires consistent visual assets across rarity tiers yet remains a predominantly manual process. We present GameUIAgent, an LLM-powered agentic framework that translates natural language descriptions into editable Figma designs via a Design Spec JSON intermediate representation. A six-stage neuro-symbolic pipeline combines LLM generation, deterministic post-processing, and a Vision-Language Model (VLM)-guided Reflection Controller (RC) for iterative self-correction with guaranteed non-regressive quality. Evaluated across 110 test cases, three LLMs, and three UI templates, cross-model analysis establishes a game-domain failure taxonomy (rarity-dependent degradation; visual emptiness) and uncovers two key empirical findings. A Quality Ceiling Effect (Pearson r=-0.96, p<0.01) suggests that RC improvement is bounded by headroom below a quality threshold -- a visual-domain counterpart to test-time compute scaling laws. A Rendering-Evaluation Fidelity Principle reveals that partial rendering enhancements paradoxically degrade VLM evaluation by amplifying structural defects. Together, these results establish foundational principles for LLM-driven visual generation agents in game production.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑