Research

Paper

AI LLM March 12, 2026

DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering

Authors

Teng Lin, Yizhang Zhu, Zhengxuan Zhang, Yuyu Luo, Nan Tang

Abstract

Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks suffer from critical limitations: standard RAG's vector similarity-based coarse-grained retrieval often omits critical facts, graph-based RAG fails to efficiently integrate fragmented complex relationship networks, and both lack schema awareness, leading to inadequate cross-document evidence chain construction and inaccurate entity relationship deduction. To address these challenges, we propose DocSage, an end-to-end agentic framework that integrates dynamic schema discovery, structured information extraction, and schema-aware relational reasoning with error guarantees. DocSage operates through three core modules: (1) A schema discovery module dynamically infers query-specific minimal joinable schemas to capture essential entities and relationships; (2) An extraction module transforms unstructured text into semantically coherent relational tables, enhanced by error-aware correction mechanisms to reduce extraction errors; (3) A reasoning module performs multi-hop relational reasoning over structured tables, leveraging schema awareness to efficiently align cross-document entities and aggregate evidence. This agentic design offers three key advantages: precise fact localization via SQL-powered indexing, natural support for cross-document entity joins through relational tables, and mitigated LLM attention diffusion via structured representation. Evaluations on two MDMEQA benchmarks demonstrate that DocSage significantly outperforms state-of-the-art long-context LLMs and RAG systems, achieving more than 27% accuracy improvements respectively.

Metadata

arXiv ID: 2603.11798
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-12
Fetched: 2026-03-14 05:03

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.11798v1</id>\n    <title>DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering</title>\n    <updated>2026-03-12T11:00:09Z</updated>\n    <link href='https://arxiv.org/abs/2603.11798v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.11798v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks suffer from critical limitations: standard RAG's vector similarity-based coarse-grained retrieval often omits critical facts, graph-based RAG fails to efficiently integrate fragmented complex relationship networks, and both lack schema awareness, leading to inadequate cross-document evidence chain construction and inaccurate entity relationship deduction. To address these challenges, we propose DocSage, an end-to-end agentic framework that integrates dynamic schema discovery, structured information extraction, and schema-aware relational reasoning with error guarantees. DocSage operates through three core modules: (1) A schema discovery module dynamically infers query-specific minimal joinable schemas to capture essential entities and relationships; (2) An extraction module transforms unstructured text into semantically coherent relational tables, enhanced by error-aware correction mechanisms to reduce extraction errors; (3) A reasoning module performs multi-hop relational reasoning over structured tables, leveraging schema awareness to efficiently align cross-document entities and aggregate evidence. This agentic design offers three key advantages: precise fact localization via SQL-powered indexing, natural support for cross-document entity joins through relational tables, and mitigated LLM attention diffusion via structured representation. Evaluations on two MDMEQA benchmarks demonstrate that DocSage significantly outperforms state-of-the-art long-context LLMs and RAG systems, achieving more than 27% accuracy improvements respectively.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-12T11:00:09Z</published>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Teng Lin</name>\n    </author>\n    <author>\n      <name>Yizhang Zhu</name>\n    </author>\n    <author>\n      <name>Zhengxuan Zhang</name>\n    </author>\n    <author>\n      <name>Yuyu Luo</name>\n    </author>\n    <author>\n      <name>Nan Tang</name>\n    </author>\n  </entry>"
}