Towards Knowledgeable Deep Research: Framework and Benchmark
Abstract
Deep Research (DR) requires LLM agents to autonomously perform multi-step information seeking, processing, and reasoning to generate comprehensive reports. In contrast to existing studies that mainly focus on unstructured web content, a more challenging DR task should additionally utilize structured knowledge to provide a solid data foundation, facilitate quantitative computation, and lead to in-depth analyses. In this paper, we refer to this novel task as Knowledgeable Deep Research (KDR), which requires DR agents to generate reports with both structured and unstructured knowledge. Furthermore, we propose the Hybrid Knowledge Analysis framework (HKA), a multi-agent architecture that reasons over both kinds of knowledge and integrates the texts, figures, and tables into coherent multimodal reports. The key design is the Structured Knowledge Analyzer, which utilizes both coding and vision-language models to produce figures, tables, and corresponding insights. To support systematic evaluation, we construct KDR-Bench, which covers 9 domains, includes 41 expert-level questions, and incorporates a large number of structured knowledge resources (e.g., 1,252 tables). We further annotate the main conclusions and key points for each question and propose three categories of evaluation metrics including general-purpose, knowledge-centric, and vision-enhanced ones. Experimental results demonstrate that HKA consistently outperforms most existing DR agents on general-purpose and knowledge-centric metrics, and even surpasses the Gemini DR agent on vision-enhanced metrics, highlighting its effectiveness in deep, structure-aware knowledge analysis. Finally, we hope this work can serve as a new foundation for structured knowledge analysis in DR agents and facilitate future multimodal DR studies.
Cite
@article{arxiv.2604.07720,
title = {Towards Knowledgeable Deep Research: Framework and Benchmark},
author = {Wenxuan Liu and Zixuan Li and Long Bai and Chunmao Zhang and Fenghui Zhang and Zhuo Chen and Wei Li and Yuxin Zuo and Fei Wang and Bingbing Xu and Xuhui Jiang and Jin Zhang and Xiaolong Jin and Jiafeng Guo and Tat-Seng Chua and Xueqi Cheng},
journal= {arXiv preprint arXiv:2604.07720},
year = {2026}
}