paperbot · PL 论文追踪

全部论文 待读 收藏

P2 A Multimodal Intelligent Change Assessment Framework for Microservice Systems Based on Large Language Models

基于大语言模型的微服务系统多模态智能变更评估框架
FSE Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering2025匹配度 2/10 · 论文将 LLM/RAG 用于微服务变更评估、故障分诊与根因分析，属于 AIOps/软件运维方向，不涉及静态分析、形式化验证、浮点程序分析或贝叶斯程序分析，也未聚焦 Agentic 程序或 ML 系统代码分析。虽然包含工业落地和 LLM 工具使用，但与研究方向核心匹配度低。引用 2 inbox
Yongqian Sun, Tinghua Zheng, Xidao Wen, Weihua Kuang, Heng Liu, Shenglin Zhang, Chao Shen, Bo Wu, Dan Pei
机器学习与程序语言分布式与容错
crossref: 2026-09-12

AI 速览

一句话：提出基于 LLM 与 RAG 的多模态变更评估框架，自动化微服务变更管理，显著降低错误变更处理时间。

大规模在线服务系统频繁变更易引发故障，威胁可靠性。现有技术在错误变更检测、故障分诊和根因变更分析上仍有不足。本文提出基于大语言模型的多模态智能变更评估框架，集成检索增强生成（RAG）、多模态数据统一表示、增强知识访问和领域专用 LLM，实现变更管理全生命周期自动化。在两个微服务系统数据集上，该方法在准确性、效率和减少人工干预方面优于现有最佳方法；名为 SCELM 的系统在真实环境运行超 11 个月，使错误变更响应与解决时间降低 90%，显著提升事件处理效率。这为变更管理与系统稳定性优化提供了实用方案。

问题
大规模在线服务系统频繁变更容易导致故障，现有技术在错误变更检测、故障分诊和根因变更分析方面存在局限。
方法
提出基于大型语言模型的多模态智能变更评估框架，集成 RAG、多模态数据统一表示、增强知识访问和领域专用 LLM，以自动化变更管理全生命周期。
评估
在两个微服务系统数据集上与现有最佳方法比较准确性、效率和人工干预程度，并在真实环境中部署 SCELM 超过 11 个月进行验证。
原文摘要（Abstract）

Frequent changes in large-scale online service systems often lead to failures, threatening system reliability. To overcome the limitations of existing techniques in erroneous change detection, failure triage, and root cause change analysis, this paper presents a multimodal intelligent change assessment framework based on large language models. Our framework integrates retrieval-augmented generation techniques and leverages unified representation of multimodal data, enhanced knowledge access, and domain-specific LLMs to automate the entire change management lifecycle. Experiments on two microservice system datasets show that our method outperforms state-of-the-arts in accuracy, efficiency, and minimizing manual intervention. Furthermore, SCELM has been operational for over 11 months in real world, reducing response and resolution times for erroneous changes by 90%, significantly improving incident handling efficiency. This work provides a robust solution for change management and valuable insights into improving system stability and optimizing operational workflows.

链接与引用

DOI 原文 ·

BibTeX 
@inproceedings{paperbot9136,
  title = {A Multimodal Intelligent Change Assessment Framework for Microservice Systems Based on Large Language Models},
  author = {Yongqian Sun and Tinghua Zheng and Xidao Wen and Weihua Kuang and Heng Liu and Shenglin Zhang and Chao Shen and Bo Wu and Dan Pei},
  booktitle = {FSE},
  year = {2025},
  doi = {10.1145/3696630.3728561}
}