arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.07342cs.AI
收藏

基于电信和数据中心基础设施的代理诊断推理

From Structured Graphs to Unstructured Evidence: Agentic Root Cause Analysis on Digital Twins

Ni2 Innovation Lab(Ni2创新实验室)

Nicolas Tacheny

AI总结:

本文提出基于代理的诊断框架,利用LLM通过MCP协议自主导航基础设施模型,实现故障诊断与影响发现,为自主事件解决和风险预测提供基础。

摘要:

大规模的电信和数据中心基础设施依赖于多层的服务和资源模型,其中故障在物理和逻辑组件之间传播,并影响多个客户。传统的根本原因分析(RCA)方法依赖于硬编码的图遍历算法或基于规则的相关性引擎,这些方法维护成本高且紧密耦合于基础设施模型。在本工作中,我们引入了一个代理诊断框架,其中大型语言模型(LLM)通过通过模型上下文协议(MCP)暴露的受限工具空间进行分步调查。而不是将因果逻辑或遍历算法嵌入应用中,代理通过调用用于服务查找、依赖检索、结构化和非结构化数据以及事件分析和影响发现的工具,自主导航基础设施模型。我们定义了一个调查协议,以结构化代理的推理并确保基础性、可重复性和安全处理缺失或模糊信息。本工作为自主事件解决和变更影响缓解奠定了基础。未来系统不仅能够诊断和修复基础设施故障,还能预测计划变更对服务和客户的影响,使运营商能够在执行维护操作前缓解风险。

英文摘要:

Root cause analysis over telecom and datacenter infrastructures is commonly addressed by methods that consume structured data, from graph traversal and rule-based correlation to probabilistic and learned models. Yet a digital twin of such an infrastructure cannot model everything at a reasonable cost. Operators therefore record much of what changes as unstructured data attached to the graph, where the discriminating evidence often sits. Methods restricted to structured attributes cannot use it. A diagnosis needs a layer that interprets this data. An agentic layer is a natural candidate, since which fragment matters depends on hypotheses that emerge during the investigation. We demonstrate its feasibility with ReAct, the most widely used agentic architecture. A single LLM interprets the descriptions and explores the graph through a typed tool interface exposed via the Model Context Protocol (MCP). On a benchmark of nine synthetic scenarios covering single-node, multi-node and distractor-heavy evidence (360 runs across four LLMs), a frontier-tier model names the root cause and its type on every run. It reaches 96.7% end-to-end diagnostic accuracy, which also requires the exact supporting evidence. A mid-tier model reaches 86.7%. Accuracy drops for every model when the evidence must be combined across several resources.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑