一句话：提出 CodeLLM-Devkit，统一集成多语言静态分析工具，为代码大模型自动提炼程序分析上下文。
代码大模型（code LLM）已在补全、生成、摘要、测试生成与翻译等任务中展现能力，但发挥其潜力需要向模型提供代码特定的上下文信息，这些信息通常来自程序分析工具。然而现有静态分析工具往往与特定编程语言绑定，学习曲线陡峭，且配置与集成到开发环境的过程复杂，开发者不得不学习和管理多个工具才能覆盖代码库的不同方面，这严重限制了静态分析与 LLM 结合的效果。为此，论文提出 CodeLLM-Devkit 框架，旨在统一抽象并集成多种程序分析工具，自动将分析结果提炼为可供代码 LLM 使用的上下文，从而降低使用门槛。摘要主要阐述该问题与框架设计动机，未报告具体的实验评估或定量结果。
Large Language Models for Code (or code LLMs) are increasingly gaining popularity and capabilities, offering a wide array of functionalities such as code completion, code generation, code summarization, test generation, code translation, and more. To leverage code LLMs to their full potential, developers must provide code-specific contextual information to the models. These are typically derived and distilled using program analysis tools. However, there exists a significant gap—these static analysis tools are often language-specific and come with a steep learning curve, making their effective use challenging. These tools are tailored to specific program languages, requiring developers to learn and manage multiple tools to cover various aspects of the their code base. Moreover, the complexity of configuring and integrating these tools into the existing development environments add an additional layer of difficulty. This challenge limits the potential benefits that could be gained from more widespread and effective use of static analysis in conjunction with LLMs.
@inproceedings{paperbot9063,
title = {Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insights},
author = {Rahul Krishna and Rangeet Pan and Saurabh Sinha and Srikanth Tamilselvam and Raju Pavuluri and Maja Vukovic},
booktitle = {FSE},
year = {2025},
doi = {10.1145/3696630.3728555}
}