Generative Knowledge-Graph Assistants for Service-Desk Incident Triage

Modern enterprise service desks are burdened with high incident volumes, inconsistent triage accuracy, and extended resolution times. This paper introduces a novel framework combining generative AI with dynamic knowledge graphs to streamline incident triage in IT service management (ITSM) environments. The proposed system leverages real-time graph-based context retrieval from CMDBs, historical tickets, and dependency maps to enable LLM-driven agents to understand, classify, and route incidents with minimal human intervention. By integrating graph embeddings with generative prompting strategies, the assistant adapts to evolving service environments and improves root-cause correlation. Evaluations on real-world ITSM datasets demonstrate a 73% reduction in triage time, a 41% increase in first-call resolution accuracy, and significant gains in knowledge reuse. The results underline the potential of agentic knowledge-graph architectures to transform reactive service desks into proactive resolution engines.