AI Insight
Researchers developed SEGRA, an AI agent that converts natural language questions into Gremlin database queries for enterprise IT support systems without requiring users to understand complex graph database syntax. The system uses a skill library that learns from past successful queries, combines schema-aware query generation with verification steps, and achieved 7 times higher accuracy than standard prompting methods. Additionally, the reusable skill library reduced AI processing costs by 18% while maintaining answer quality on enterprise IT support benchmarks.
Why it matters
This technology could make enterprise knowledge graphs accessible to non-technical support staff, reducing the expertise barrier for querying complex IT databases. The cost and efficiency improvements demonstrate practical viability for real-world deployment in enterprise environments where reducing reliance on specialized database knowledge can improve operational efficiency.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historical resolutions. Yet querying them in Gremlin requires knowledge of graph schemas, traversal semantics, edge directionality, and property-graph-specific constraints, making them difficult for non-expert operators to use. We introduce SEGRA, an experience-guided agent for enterprise text-to-Gremlin question answering. SEGRA integrates intent routing, schema- and taxonomy-grounded query generation, multi-shot decomposition, execution-aware verification, and a curriculum-bootstrapped skill library that reuses verified query patterns. On an enterprise IT support benchmark, SEGRA achieves a $7.0times$ higher mean judge score than backbone-only chain-of-thought prompting. Its skill library further reduces LLM calls by $20%$ and dollar cost by $18%$ relative to SEGRA without skills, while preserving answer quality. These results show that schema-grounded agent design and reusable execution experience improve both accuracy and efficiency for enterprise graph QA.
Source: SEGRA: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering