一句话：提出用 LLM 编辑聚类为遗传改进注入语义信号，并以 PatchCat 初步验证其可行性与效率收益。
遗传改进（GI）能自动生成按运行时间等目标性质优化的软件版本，擅长在巨大程序空间中搜索，但其操作主要停留在语法层面；大语言模型（LLM）可给出语义感知的编辑，却缺乏目标导向的反馈与控制，而这恰是 GI 的强项。本文提出一条 AI 驱动的 GI 新研究路线，旨在把语义感知搜索引入 GI，并迈出第一步：用自动聚类来组织 LLM 产生的编辑。作者给出初步实证，表明名为 PatchCat 的方案能自动且有效地对 LLM 建议的补丁进行分类，共识别出 18 种软件补丁类型，并以高准确率归类新补丁；它还能提前检测 NoOp 编辑，从而在许多情形下跳过测试套件执行以节省资源。由于 PatchCat 可运行于小型本地 LLM，这些结果被视为通向可解释、高效、绿色 GI 的有希望的一步，作者同时给出了丰富的未来工作议程。
Genetic Improvement (GI) of software automatically creates alternative software versions that are improved according to certain properties of interests (e.g., running-time). Search-based GI excels at navigating large program spaces, but operates primarily at the syntactic level. In contrast, Large Language Models (LLMs) offer semantic-aware edits, yet lack goal-directed feedback and control (which is instead a strength of GI).As such, we propose the investigation of a new research line on AI-powered GI aimed at incorporating semantic aware search. We take a first step at it by augmenting GI with the use of automated clustering of LLM edits.We provide initial empirical evidence that our proposal, dubbed PatchCat, allows us to automatically and effectively categorize LLM-suggested patches. PatchCat identified 18 different types of software patches and categorized newly suggested patches with high accuracy. It also enabled detecting NoOp edits in advance and, prospectively, to skip test suite execution to save resources in many cases. These results, coupled with the fact that PatchCat works with small, local LLMs, are a promising step toward interpretable, efficient, and green GI.We outline a rich agenda of future work and call for the community to join our vision of building a principled understanding of LLM-driven mutations, guiding the GI search process with semantic signals.
DOI 原文 ·
@inproceedings{paperbot9359,
title = {LLM-Guided Genetic Improvement: Envisioning Semantic Aware Automated Software Evolution},
author = {Karine Even-Mendoza and Alexander Brownlee and Alina Geiger and Carol Hanna and Justyna Petke and Federica Sarro and Dominik Sobania},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00339}
}