Agentic Diagnostic Reasoning over Telecom and Datacenter Infrastructure
Nicolas Tacheny
TL;DR
RCA and IA in large telecom/datacenter infrastructures are challenged by brittle, hard-coded graph-based approaches. The authors propose a tool-grounded, agentic framework in which an LLM performs diagnostic reasoning entirely through a fixed MCP toolset, with the infrastructure modeled as a typed graph $G=(V,E,\tau_V,\tau_E)$ and reasoning grounded in tool outputs. They define an RCA Investigation Protocol and demonstrate that root-cause and impact inferences can emerge without embedding graph algorithms, validated through an Oracle Benchmark across multiple models and safety/faithfulness evaluations. The approach decouples reasoning from data storage via a Digital Twin and MCP-based deployment, enabling autonomous incident resolution and proactive change impact mitigation, while outlining future work on temporal reasoning, RAG integration, and automated remediation.
Abstract
Large-scale telecom and datacenter infrastructures rely on multi-layered service and resource models, where failures propagate across physical and logical components and affect multiple customers. Traditional approaches to root cause analysis(RCA) rely on hard-coded graph traversal algorithms or rule-based correlation engines, which are costly to maintain and tightly coupled to the infrastructure model. In this work, we introduce an agentic diagnostic framework where a Large Language Model (LLM) performs step-wise investigation using a constrained tool space exposed through the Model Context Protocol (MCP). Instead of embedding causal logic or traversal algorithms into the application, the agent autonomously navigates the infrastructure model by invoking tools for service lookup, dependency retrieval, structured and unstructured data, and event analysis, and impact discovery. We define an investigation protocol that structures the agent's reasoning and ensures grounding, reproducibility, and safe handling of missing or ambiguous information. This work lays the foundation for autonomous incident resolution and change impact mitigation. Future systems will not only diagnose and remediate infrastructure failures, but also predict the impact of planned changes on services and customers, enabling operators to mitigate risks before executing maintenance operations.