一句话：将积木式 Scratch 代码转为文本表示并接入 LLM，扩展 LitterBox 静态分析以支持问答与自动修复。
大语言模型已成为文本编程语言开发者的重要辅助工具，但 Scratch 等积木式编程环境的图形化表示阻碍了 LLM 的直接使用。为此，作者提出 LitterBox+，在 Scratch 静态代码分析工具 LitterBox 的基础上引入 LLM 的生成能力。该框架将积木代码转换为适合 LLM 处理的文本表示，使用户能够就程序本身、LitterBox 报告的质量问题向 LLM 提问，并生成代码修复建议。除提供编程 API 外，LitterBox+ 还将这些功能集成到 Scratch 用户界面中，使学习者可在熟悉的环境内直接使用。框架设计强调可扩展性，支持添加新的提示、其他 LLM 提供者，以及结合程序分析与生成能力的新特性。作者通过 screencast 演示该工具，摘要未报告用户研究或量化评估结果。
Large language models (LLMS) have become an essential tool to support developers using traditional text-based programming languages, but the graphical notation of the block-based Scratch programming environment inhibits the use of LLMs. To overcome this limitation, we propose the LitterBox+framework that extends the Scratch static code analysis tool LitterBox with the generative abilities of LLMs. By converting block-based code to a textual representation suitable for LLMs, LitterBox+allows users to query LLMs about their programs, about quality issues reported by LitterBox, and it allows generating code fixes. Besides offering a programmatic API for these functionalities, LitterBox+also extends the Scratch user interface to make these functionalities available directly in the environment familiar to learners. The framework is designed to be easily extensible with other prompts, LLM providers, and new features combining the program analysis capabilities of LitterBox with the generative features of LLMs. We provide a screencast demonstrating the tool at https://youtu.be/RZ6E0xgrIgQ.
@inproceedings{paperbot9198,
title = {LitterBox
<sup>+</sup>
: An Extensible Framework for LLM-enhanced Scratch Static Code Analysis},
author = {Benedikt Fein and Florian Obermüller and Gordon Fraser},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00357}
}