PaperScope
LIVE · 2026-09-29 05:40 UTC

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

Jiaming Tian, Liyao Li, Wentao Ye, Haobo Wang, Lihua Yu, Zujie Ren, Gang Chen, Junbo Zhao

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.34157 v1
Category
Submitted
2026-09-28

Abstract

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.

arXiv abs page · PDF · same-day batch