Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910014269030400 |
|---|---|
| author | Lan, Tian Henry, Felix Zhu, Bin Jia, Qianghuai Ren, Junyang Pu, Qihang Li, Haijun Wang, Longyue Xu, Zhao Luo, Weihua |
| author_facet | Lan, Tian Henry, Felix Zhu, Bin Jia, Qianghuai Ren, Junyang Pu, Qihang Li, Haijun Wang, Longyue Xu, Zhao Luo, Weihua |
| contents | Current Information Seeking (InfoSeeking) agents struggle to maintain focus and coherence during long-horizon exploration, as tracking search states, including planning procedure and massive search results, within one plain-text context is inherently fragile. To address this, we introduce \textbf{Table-as-Search (TaS)}, a structured planning framework that reformulates the InfoSeeking task as a Table Completion task. TaS maps each query into a structured table schema maintained in an external database, where rows represent search candidates and columns denote constraints or required information. This table precisely manages the search states: filled cells strictly record the history and search results, while empty cells serve as an explicit search plan. Crucially, TaS unifies three distinct InfoSeeking tasks: Deep Search, Wide Search, and the challenging DeepWide Search. Extensive experiments demonstrate that TaS significantly outperforms numerous state-of-the-art baselines across three kinds of benchmarks, including multi-agent framework and commercial systems. Furthermore, our analysis validates the TaS's superior robustness in long-horizon InfoSeeking, alongside its efficiency, scalability and flexibility. Code and datasets are publicly released at https://github.com/AIDC-AI/Marco-Search-Agent. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06724 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completion Lan, Tian Henry, Felix Zhu, Bin Jia, Qianghuai Ren, Junyang Pu, Qihang Li, Haijun Wang, Longyue Xu, Zhao Luo, Weihua Computation and Language Current Information Seeking (InfoSeeking) agents struggle to maintain focus and coherence during long-horizon exploration, as tracking search states, including planning procedure and massive search results, within one plain-text context is inherently fragile. To address this, we introduce \textbf{Table-as-Search (TaS)}, a structured planning framework that reformulates the InfoSeeking task as a Table Completion task. TaS maps each query into a structured table schema maintained in an external database, where rows represent search candidates and columns denote constraints or required information. This table precisely manages the search states: filled cells strictly record the history and search results, while empty cells serve as an explicit search plan. Crucially, TaS unifies three distinct InfoSeeking tasks: Deep Search, Wide Search, and the challenging DeepWide Search. Extensive experiments demonstrate that TaS significantly outperforms numerous state-of-the-art baselines across three kinds of benchmarks, including multi-agent framework and commercial systems. Furthermore, our analysis validates the TaS's superior robustness in long-horizon InfoSeeking, alongside its efficiency, scalability and flexibility. Code and datasets are publicly released at https://github.com/AIDC-AI/Marco-Search-Agent. |
| title | Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completion |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.06724 |