AgentOnto: Ontology-Guided LLM Agents for Enterprise Data Analytics
AgentOnto guides enterprise LLM analytics with an ontology that is built, used, and updated from feedback.
AgentOnto organizes databases, business documents, and example tasks into an ontology that guides an LLM analytics agent and incorporates confirmed user feedback. Iterative Ontology Preparation further improves that ontology using self-generated analysis tasks. Evaluations on two public data sources show substantial gains over representative methods, and a real-world deployment illustrates practical enterprise use.
- Ontology links requests to databases, documents, and examples
- Confirmed feedback is written back into the ontology
- Self-generated tasks refine ontology preparation
- Outperforms baselines on two public sources and a deployment
From the original article
1 min read at arxiv.orgEnterprise 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.
By Dayan Pan · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.