Scholarlink

AI technologies play an important role in diagnosing the performance of a service system and ensuring its continuous operation (AIOps) by detecting anomalies, localizing root causes, and adapting system configurations. Large language models (LLMs) possess broad knowledge of computing systems and offer new opportunities for effective root cause analysis and system adaptation. However, their inference capabilities for complex problems remain challenging. In this abstract, we discuss how a knowledge graph-based representation of performance anomalies, root causes, and adaptation strategies can be used to enhance LLMs in AIOps through an agentic system model.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Towards Knowledge Retrieval for Agentic Systems in Cloud: Learning, Analysis and Control

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Paul Daniëlse,
  • Shashikant Ilager,
  • Zhiming Zhao

摘要

AI technologies play an important role in diagnosing the performance of a service system and ensuring its continuous operation (AIOps) by detecting anomalies, localizing root causes, and adapting system configurations. Large language models (LLMs) possess broad knowledge of computing systems and offer new opportunities for effective root cause analysis and system adaptation. However, their inference capabilities for complex problems remain challenging. In this abstract, we discuss how a knowledge graph-based representation of performance anomalies, root causes, and adaptation strategies can be used to enhance LLMs in AIOps through an agentic system model.