发表机构
Zhejiang University; Bank of Hangzhou Co., Ltd.; Zhejiang Lab（浙江大学; 杭州银行股份有限公司; 之江实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TableSeek提出一种保持结构的智能体搜索框架，通过LLM智能体迭代追踪线索、检查模式预览并识别不匹配，在异构表格语料库上实现无需预计算索引的细粒度证据定位，取得与强检索-重排序管道相当的性能。
AI 中文摘要
开放域表格检索旨在寻找包含足够证据以回答问题或验证声明的表格。然而，语义相关性往往具有误导性：主题相似的表格可能缺乏所需事实，而包含答案的证据通常局限于少数单元格，其含义依赖于周围的模式和表格上下文。异构的模式、值格式和序列化进一步削弱了一次性匹配的效果。我们提出了TableSeek，一个针对异构表格语料库的保持结构的智能体搜索框架。不同于一次性对表格进行排序，一个LLM智能体迭代地跟随稀疏线索，检查保持模式的预览，识别模式和值层面的不匹配，并优化其调查过程。TableSeek使用单元格和模式作为证据锚点，同时保留完整表格作为证据单元，从而在不丢失解释和可回答性检查所需上下文的情况下实现细粒度定位。无需依赖检索器训练或预计算的语义索引，TableSeek产生了透明的证据搜寻轨迹，并在异构表格基准上实现了与强检索-重排序管道相当的整体性能。这些结果表明，主动的、保持结构的证据搜寻是开放域表格检索的一种有前景的范式。
英文摘要
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.
