一句话：提出两阶段意图驱动代码精化方法：先从评审评论中抽取意图，再引导 LLM 生成修订代码。
代码精化旨在通过修改问题、重构与优化来提升既有代码质量，但随着软件规模增大，评审者与开发者之间的迭代沟通成本日益沉重；已有深度学习方法因难以准确理解评审者意图而效果受限。本文提出基于意图的代码精化技术，将传统的“评论到代码”过程显式拆分为两个阶段：意图抽取与意图引导的修订生成。前者用预定义模板将评论归入 3 大类 8 个子类，并采用规则与 LLM 结合的混合分类器；后者让大语言模型依据抽取出的意图生成修订代码。作者在 5 个 LLM（GPT-4o、GPT-3.5、DeepSeekV2、DeepSeek7B、CodeQwen7B）与多种提示设置下开展实验，意图抽取准确率达 79%，代码精化生成最高达 66%，表明该方法能提升数据质量与代码精化效率。
Code refinement aims to enhance existing code by addressing issues, refactoring, and optimizing to improve quality and meet specific requirements. As software projects scale in size and complexity, the traditional iterative exchange between re-viewers and developers becomes increasingly burdensome. While recent deep learning techniques have been explored to accelerate this process, their performance remains limited, primarily due to challenges in accurately understanding reviewers' intents. This paper proposes an intention-based code refinement technique that enhances the conventional comment-to-code process by explicitly extracting reviewer intentions from the comments. Our approach consists of two key phases: Intention Extraction and Intention Guided Revision Generation. Intention Extraction categorizes comments using predefined templates, while Intention Guided Revision Generation employs large language models (LLMs) to generate revised code based on these defined intentions. Three categories with eight subcategories are designed for comment transformation, which is followed by a hybrid approach that combines rule-based and LLM-based classifiers for accurate classification. Extensive experiments with five LLMs (G PT 40, GPT3.5, DeepSeekV2, DeepSeek7B, CodeQwen7B) under different prompting settings demonstrate that our approach achieves 79 % accuracy in intention extraction and up to 66 % in code refinement generation. Our results highlight the potential of our approach in enhancing data quality and improving the efficiency of code refinement.
@inproceedings{paperbot8799,
title = {Intention is All you Need: Refining your Code from your Intention},
author = {Qi Guo and Xiaofei Xie and Shangqing Liu and Ming Hu and Xiaohong Li and Lei Bu},
booktitle = {ICSE},
year = {2025},
doi = {10.1109/icse55347.2025.00191}
}