一句话：提出首个集成 LLM 智能体的项目级资源泄漏检测框架 AROP，通过元数据筛选、智能体识别与数据流验证降低误报。
资源泄漏会造成系统性能下降甚至崩溃。传统静态分析方法依赖预定义规则，难以发现未知类型的泄漏；新兴的基于 LLM 的方法虽能定位相关 API，但在大规模项目中存在成本高、误报多等问题。为解决这些局限，本文提出 AROP——首个集成 LLM 智能体的项目级资源泄漏检测框架。AROP 首先抽取项目级元数据，以高效筛选出与资源相关的文件；随后由检测智能体识别资源的获取（acquisition）与释放（release）操作，再通过验证智能体与数据流依赖分析来减少误报；最后借助泄漏修复模式分析判定是否确实存在泄漏。该工作将 LLM 智能体与静态数据流分析结合，面向真实项目的规模与精度需求进行设计。
Resource leaks cause system performance degradation and crashes. Traditional static analysis approaches rely on predefined rules, limiting their ability to find unknown leaks. Emerging LLM-based methods can locate APIs but face challenges in large-scale projects, including high costs and numerous false positives. To address these limitations, we propose AROP, the first project-level resource leak detection framework integrating LLM-based agents. AROP first extracts project-level metadata to efficiently filter resource-related files. It then employs a detection agent to identify acquisition/release operations, followed by a validation agent and data-flow dependency analysis to reduce false positives. Finally, it determines leaks through leak repair pattern analysis.
@inproceedings{paperbot11909,
title = {Project-Level Resource Leak Detection through Agent-based Ownership Analysis and Repair Pattern Verification},
author = {Chengxin Xu and Xiu Zhang and Xiaorui Gong},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3773243}
}