arXiv cs.AI· Dayan Pan, Bincheng Zuo, Xiaojian Wang, Daogang Zhang, Jingyuan Wang·· 12 小时前AI 评分38
AgentOnto：本体引导的 LLM 智能体用于企业数据分析
AgentOnto: Ontology-Guided LLM Agents for Enterprise Data Analytics
AI 导读
AgentOnto 是一个本体引导的 LLM 智能体，将数据库、业务文档和示例任务中的异构企业知识组织成本体，直接指导分析并纳入已确认的反馈。其迭代式本体准备通过自生成分析任务改进本体，在两个公开数据源上显著优于代表性方法，模块级评估验证了本体构建、分析与更新的有效性，真实部署也体现了实用价值。
正文 · 原文
Abstract:Enterprise data analysis requires agents to connect analytical requests with knowledge distributed across databases, business documents, and existing example tasks. Without an explicit representation of this knowledge, an agent may produce incorrect analytical results and cannot reliably incorporate feedback. We present AgentOnto, an ontology-guided LLM agent for enterprise data analytics. AgentOnto organizes heterogeneous enterprise knowledge into an ontology that directly guides analysis and incorporates confirmed feedback. Iterative Ontology Preparation further improves the ontology through self-generated analysis tasks. We evaluate AgentOnto on two public data sources. AgentOnto substantially outperforms representative methods, while module-level evaluations confirm the effectiveness of ontology construction, analysis, and updating. A real-world deployment further demonstrates its practical value in enterprise analytics. These results demonstrate that explicitly constructing, using, and updating enterprise knowledge supports reliable and adaptable data analysis.
| Comments: | Under review |
| Subjects: | Artificial Intelligence (cs.AI); Databases (cs.DB) |
| Cite as: | arXiv:2610.23317 [cs.AI] |
| (or arXiv:2610.23317v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.23317 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Dayan Pan [view email]
[v1]
Fri, 16 Oct 2026 11:22:38 UTC (867 KB)
来源：arXiv cs.AI · arxiv.org