Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.09151 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918384062431232 |
|---|---|
| author | Dong, Junnan Zhou, Chuang Yuan, Zheng Yu, Yifei Wang, Qiufeng Li, Yinghui An, Siyu Yin, Di Sun, Xing Huang, Feiyue |
| author_facet | Dong, Junnan Zhou, Chuang Yuan, Zheng Yu, Yifei Wang, Qiufeng Li, Yinghui An, Siyu Yin, Di Sun, Xing Huang, Feiyue |
| contents | Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09151 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Deep Tabular Research via Continual Experience-Driven Execution Dong, Junnan Zhou, Chuang Yuan, Zheng Yu, Yifei Wang, Qiufeng Li, Yinghui An, Siyu Yin, Di Sun, Xing Huang, Feiyue Artificial Intelligence Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning. |
| title | Deep Tabular Research via Continual Experience-Driven Execution |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.09151 |