SEGRA：用于基于Gremlin的问答的结构化经验引导图推理代理
SEGRA: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering
- University of British Columbia（英属哥伦比亚大学）
- Amazon（亚马逊）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对企业文本到Gremlin问答难题，SEGRA引入经验引导代理，集成多种技术，包括意图路由、查询生成等。在企业IT支持基准测试中成绩出色，平均评判分数大幅提高，技能库还降低了成本，提升了企业图问答的准确性与效率。
AI中文摘要：
企业IT支持知识图捕捉了案例、用户、设备、症状、分类类别、根本原因和历史解决方案之间的丰富关系。然而，用Gremlin查询它们需要图模式、遍历语义、边方向性和属性图特定约束的知识，这使得非专家操作员难以使用。我们引入了SEGRA，一种用于企业文本到Gremlin问答的经验引导代理。SEGRA集成了意图路由、基于模式和分类法的查询生成、多步分解、执行感知验证以及一个课程引导的技能库，该技能库重用经过验证的查询模式。在企业IT支持基准测试中，SEGRA的平均评判分数比仅使用思维链提示高出7.0倍。其技能库相对于没有技能的SEGRA，进一步将大语言模型调用减少了20%，成本降低了18%，同时保持了答案质量。这些结果表明，基于模式的代理设计和可重用的执行经验提高了企业图问答的准确性和效率。
英文摘要：
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 $7.0\times$ 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.
