cs.AIJan 12, 2026

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

Authors: Nicolas Tacheny

Organizations: Ni2 Innovation Lab

Abstract

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.

Figures & tables

Explore similar work

CardsList
  1. DNative-Twin: Decision Graphs and Digital Twins for Reconstructable Agentic Decisions

    Sep 3, 2026Junjie Pang, Zhenzhen Xie, Haoke Han +3Data ProvenanceAI Agent Auditing

  2. Agentic Root Cause Analysis through Evidence-Grounded Reasoning

    Jul 24, 2026Amaury Wei, Olga FinkIndustrial Anomaly DetectionAgentic Reasoning