用大模型自动造谜题游戏，还能自测自改。
ScriptDoctor: Automatic Generation of PuzzleScript Games via Large Language Models and Tree Search
- 大模型生成代码，引擎报错反哺优化。
- 迭代生成+自动测试，实现闭环设计。
- 适合对游戏生成感兴趣的开发者。
当前大型预训练模型在自动游戏设计（AGD）中备受关注，可用于生成代码、资源或抽象设计概念。然而，这些应用大多依赖人工持续监督，缺乏长期自主运行的流程。为此，我们提出ScriptDoctor，一个基于大语言模型（LLM）的系统，用于在PuzzleScript这一高度受限的二维网格迷题游戏描述语言中，自动生成并测试游戏。该系统通过迭代循环实现：以人类编写示例为起点，利用PuzzleScript引擎的编译错误反馈生成可运行代码，并由搜索代理自动试玩新生成的游戏。ScriptDoctor展示了基于大模型的自动化、开放式工作流在生成新颖游戏内容方面的潜力。
原文摘要 · Abstract (English)
There is much interest in using large pre-trained models in Automatic Game Design (AGD), whether via the generation of code, assets, or more abstract conceptualization of design ideas. But so far this interest largely stems from the ad hoc use of such generative models under persistent human supervision. Much work remains to show how these tools can be integrated into longer-time-horizon AGD pipelines, in which systems interface with game engines to test generated content autonomously. To this end, we introduce ScriptDoctor, a Large Language Model (LLM)-driven system for automatically generating and testing games in PuzzleScript, an expressive but highly constrained description language for turn-based puzzle games over 2D gridworlds. ScriptDoctor generates and tests game design ideas in an iterative loop, where human-authored examples are used to ground the system's output, compilation errors from the PuzzleScript engine are used to elicit functional code, and search-based agents play-test generated games. ScriptDoctor serves as a concrete example of the potential of automated, open-ended LLM-based workflows in generating novel game content.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。