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

2026-02-06

AI Summary

This work addresses the challenge that long-horizon information-seeking agents in purely textual environments struggle to maintain effective search states, leading to unfocused and incoherent exploration. To overcome this limitation, the authors reformulate the task as a structured table-filling problem, unifying information seeking under the paradigm of table completion for the first time. By leveraging an external database to explicitly store and update search plans, candidate results, and constraints, the approach enables precise tracking and dynamic planning of the search state. The proposed method supports three distinct search paradigms—Deep Search, Wide Search, and the more challenging DeepWide Search—and significantly outperforms existing state-of-the-art multi-agent frameworks and commercial systems across all three benchmark settings, demonstrating superior efficiency, scalability, and capability in handling long-horizon tasks.

Technology Category

• Search and Optimization: Learning to Search
• Multiagent Systems: Multiagent Planning
• Constraint Satisfaction and Optimization: Search

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

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.

Problem

• Information Seeking
• Long-Horizon Exploration
• Search State Management
• Agent Coherence
• Structured Planning

Innovation

• Table-as-Search
• structured planning
• information seeking
• table completion
• long-horizon reasoning