Metraipolis › archive › dc_9b960d005e1d

OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes — arXiv:2611.12114

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.12114
License (as archived)
CC0-1.0
Archived
2026-11-10T18:41:44.198Z
SHA-256 of the archived text
b28fc8e34d1e3f66d1c726cf129eb499a3383a569efb2f10e202f56831a5fcf9
Stable URL of this page
https://metraipolis.com/documento/dc_9b960d005e1d

How to cite

OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes — arXiv:2611.12114 — arXiv (en), https://arxiv.org/abs/2611.12114 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9b960d005e1d (Metraipolis archive dc_9b960d005e1d, sha256 b28fc8e34d1e3f66d1c726cf129eb499a3383a569efb2f10e202f56831a5fcf9)
BibTeX
@misc{dc9b960d005e1d,
  title = {OGDA: Ontology-Grounded Data Agents for Reliable Analysis over Heterogeneous Data Lakes — arXiv:2611.12114},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.12114},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9b960d005e1d; sha256 b28fc8e34d1e3f66d1c726cf129eb499a3383a569efb2f10e202f56831a5fcf9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12114. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.12114 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-10T18:37:37.536Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).