Metraipolis › archive › dc_84d2c19f01ce

TableSeek: Structure-Preserving Agentic Evidence Seeking over Heterogeneous Table Corpora — arXiv:2609.34157

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.34157
License (as archived): CC0-1.0
Archived: 2026-10-07T20:57:28.192Z
SHA-256 of the archived text: 66e580c1717667bd9017b739776667dcd2cc32eb3dc0855507563c0e7c392ade
Stable URL of this page: https://metraipolis.com/documento/dc_84d2c19f01ce

How to cite

TableSeek: Structure-Preserving Agentic Evidence Seeking over Heterogeneous Table Corpora — arXiv:2609.34157 — arXiv (en), https://arxiv.org/abs/2609.34157 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84d2c19f01ce (Metraipolis archive dc_84d2c19f01ce, sha256 66e580c1717667bd9017b739776667dcd2cc32eb3dc0855507563c0e7c392ade)

BibTeX

@misc{dc84d2c19f01ce,
  title = {TableSeek: Structure-Preserving Agentic Evidence Seeking over Heterogeneous Table Corpora — arXiv:2609.34157},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34157},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84d2c19f01ce; sha256 66e580c1717667bd9017b739776667dcd2cc32eb3dc0855507563c0e7c392ade},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34157. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Open-domain table retrieval seeks tables that contain sufficient evidence for answering a question or verifying a claim. Yet semantic relevance is often misleading: topically similar tables may lack the required facts, while answer-bearing evidence is often confined to a few cells whose meaning depends on surrounding schema and table context. Heterogeneous schemas, value formats, and serializations further weaken one-shot matching. We present TableSeek, a structure-preserving agentic search framework for heterogeneous table corpora. Instead of ranking tables once, an LLM agent iteratively follows sparse clues, inspects schema-preserving previews, identifies schema- and value-level mismatches, and refines its investigation. TableSeek uses cells and schemas as evidence anchors while retaining complete tables as evidence units, enabling fine-grained localization without losing the context required for interpretation and answerability checking. Without relying on retriever training or a precomputed semantic index, TableSeek produces transparent evidence-seeking trajectories and achieves competitive end-to-end performance against strong retrieval-and-reranking pipelines on heterogeneous table benchmarks. These results suggest that active, structure-preserving evidence seeking is a promising paradigm for open-domain table retrieval.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.34157 — 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 2026-10-07T20:29:01.456Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).