cs.AINov 9, 2026

OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes

Authors: Boyi Zhang, Hong Ting Tsang, Yisen Gao, Qiao Xiao, LI Yufei, Haoyu Huang, Zhongwei Xie, Jiaxin Bai, 

Organizations: The Hong Kong University of Science and Technology · Hong Kong Baptist University

Abstract

Full-pipeline data analysis over real-world data lakes requires LLM agents to locate and integrate information across large collections of tables with different schemas. Existing data agents follow task-specific exploration, which exhausts the context window in massive lakes. As the context fills, the agent's reasoning degrades, leading it to locate and process incorrect data files. These errors propagate into the final answer. To overcome these limitations, we introduce Ontology-Grounded Data Agent (OGDA), which utilizes a compact ontology to reduce exploration overhead and constrain data processing. OGDA constructs the ontology through agentic hypothesis testing. At each step, a proposer agent induces schemas, concepts, and relations from raw sources, and a verifier checks each proposal against the underlying data. During task execution, the ontology serves as a representation of the data lake for the agent to explore. Every data-processing action is constrained by a task graph, which the agent can extend only after observing the semantic meaning of the data. Across KramaBench and DiscoveryBench with three LLM backbones, OGDA outperforms the strongest baselines by up to 10.82 points. These results suggest that explicitly modeling the data lake is a key step toward reliable end-to-end data agents.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AgentOnto: Ontology-Guided LLM Agents for Enterprise Data Analytics

    Oct 16, 2026Dayan Pan, Bincheng Zuo, Xiaojian Wang +2Enterprise AnalyticsData Analysis Agents

  2. SANA: What Matters for QA Agents over Massive Data Lakes?

    Jun 11, 2026Austin Senna Wijaya, Jiaxiang Liu, Haonan Wang +1LLM Agent EvaluationQuestion Answering

  3. EvoOntology: A Self-Evolving Ontology Layer for Data Agents

    Sep 14, 2026Meiduo Chong, Shaolei Zhang, Ju Fan +1LLM Agent Self-ImprovementSelf-Evolving Agents