面向持续游戏生成的GUI智能体
GUI Agents for Continual Game Generation
AI总结：
提出利用GUI智能体作为客观评估者和主观测试者，通过PlaytestArena和Play2Code框架实现持续游戏生成，显著提升可玩性。
摘要：
生成一个游戏与制作一个可玩的游戏不同。尽管代码生成取得了进展，现有方法将游戏生成视为从提示到产物的单次翻译，导致交互层面的失败未被检测。我们认为评估和改进游戏生成需要一个玩家，并研究了图形用户界面（GUI）智能体在此过程中的两个角色：（1）作为客观评估者，为此我们引入了PlaytestArena，这是一个新的评估环境，将8个游戏类型的200个基于浏览器的游戏生成任务与预期的游戏行为准则配对，由GUI智能体在浏览器中加载每个构建并玩它来裁决；（2）作为主观测试者，为此我们提出了Play2Code，其中游戏智能体和GUI智能体在共享内存的持续循环中运行，将游戏生成转化为编码和游戏之间的对话。我们的实验表明，即使是前沿模型也难以直接生成可玩的游戏，而Play2Code达到了66.8%的准则通过率，分别比单次传递和智能体编码基线提高了37.1和14.6个百分点。进一步分析表明，GUI测试者的反馈比人类报告更可追溯，但在某些方面具有类似人类测试者的特质，将游戏测试确立为交互式代码生成的关键测试平台。我们的项目网站位于https://continual-game-generation.vercel.app/。
英文摘要：
Generating a game is not the same as making one playable. Existing code-generation approaches often translate a prompt directly into an artifact, leaving interaction-level failures undetected. We argue that game generation requires a player and study two roles for graphical user interface (GUI) agents. First, we introduce \textbf{PlaytestArena}, an evaluation environment containing 200 browser-based game-generation tasks across eight genres, each paired with rubrics of expected in-play behaviors. An independent GUI judge loads and plays each build to adjudicate these rubrics. Second, we propose \textbf{Play2Code}, in which a game agent and a rubric-blind GUI playtester iteratively generate, play, and refine games through shared memory. The playtester provides gameplay traces and actionable feedback, while a separate GPT-5.5 judge assigns final benchmark scores. Across three frontier backbones, Play2Code achieves a 66.8\% rubric pass rate, outperforming single-pass and agentic-coding baselines by 37.1 and 14.6 points, respectively. Its scores also improve monotonically across refinement rounds. Further analysis shows that GUI-agent feedback is fully logged and traceable, while its priorities vary substantially across model backbones. These results establish GUI playtesting as an evaluation and refinement signal for interactive code generation. Our project website is available at https://continual-game-generation.vercel.app/
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。
