Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completion

TL;DR

This paper introduces Table-as-Search (TaS), a structured framework that reformulates long-horizon information seeking as a table completion task, improving focus, coherence, and robustness in search agents.

Contribution

TaS unifies multiple InfoSeeking tasks into a table completion framework, enabling better management of search states and significantly outperforming existing methods.

Findings

TaS outperforms state-of-the-art baselines across benchmarks.

TaS demonstrates superior robustness in long-horizon InfoSeeking.

TaS offers improved efficiency, scalability, and flexibility.

Abstract

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.