一句话：利用分析规则中的谓词检索关键样例，构建 RAG 流水线自动修复静态分析告警，显著提升 LLM 修复正确率。
用大语言模型（LLM）修复静态分析告警日益流行，但 LLM 容易产生幻觉，对复杂、罕见告警表现不佳。检索增强生成（RAG）通过提供相关示例缓解该问题，但现有方法所检索示例的质量往往不理想。本文观察到静态分析规则的谓词可作为告警与干净代码库中相关代码片段（称为关键示例）之间的桥梁，据此提出自动检索告警关键示例的算法，并构建 PredicateFix 作为 RAG 流水线，用于修复 CodeQL 与 GoInsight 两个静态代码分析器的告警。在多个 LLM 上的评估表明，PredicateFix 将正确修复数量提升 27.1%～69.3%，显著优于其他基线 RAG 方法。
Fixing static analysis alerts in source code with Large Language Models (LLMs) is becoming increasingly popular. However, LLMs often hallucinate and perform poorly for complex and less common alerts. Retrieval-augmented generation (RAG) techniques aim to solve this problem by providing the model with a relevant example, but existing approaches face the challenge of unsatisfactory quality of such examples. To address this challenge, we utilize the predicates in the analysis rule, which serve as a bridge between the alert and relevant code snippets within a clean code corpus, called key examples. Based on this insight, we propose an algorithm to retrieve key examples for an alert automatically, and build PredicateFix as a RAG pipeline to fix alerts from two static code analyzers: CodeQL and GoInsight. Evaluation with multiple LLMs shows that PredicateFix increases the number of correct repairs by \(27.1\% \sim 69.3\%\), significantly outperforming other baseline RAG approaches.
@inproceedings{abs-2503-12205,
title = {PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates},
author = {Yuan-An Xiao and Weixuan Wang and Dong Liu and Junwei Zhou and Shengyu Cheng and Yingfei Xiong},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3773159}
}