IoDResearch: Deep Research on Private Heterogeneous Data via the Internet of Data

2025-10-01

AI Summary

Existing deep research frameworks predominantly focus on web-scale search, neglecting private, heterogeneous scientific data—resulting in inefficient retrieval, poor compliance with FAIR principles, and limited reusability. To address this, we propose IoDResearch, a framework centered on private data and grounded in the Internet of Data (IoD) paradigm. It encapsulates heterogeneous data as FAIR-compliant digital objects and decomposes them into atomic knowledge units and dynamic knowledge graphs. By integrating digital object architecture, heterogeneous graph indexing, and multi-agent collaboration, IoDResearch enables trustworthy question answering and automated scientific report generation. Experiments demonstrate significant improvements over state-of-the-art RAG and deep research baselines across retrieval, QA, and report generation tasks. Furthermore, we release the first IoD DeepResearch benchmark to advance automated, reusable, private-data-driven scientific discovery.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Search and Optimization: Distributed Search
• Knowledge Representation and Reasoning: Other Foundations of Knowledge Representation & Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

The rapid growth of multi-source, heterogeneous, and multimodal scientific data has increasingly exposed the limitations of traditional data management. Most existing DeepResearch (DR) efforts focus primarily on web search while overlooking local private data. Consequently, these frameworks exhibit low retrieval efficiency for private data and fail to comply with the FAIR principles, ultimately resulting in inefficiency and limited reusability. To this end, we propose IoDResearch (Internet of Data Research), a private data-centric Deep Research framework that operationalizes the Internet of Data paradigm. IoDResearch encapsulates heterogeneous resources as FAIR-compliant digital objects, and further refines them into atomic knowledge units and knowledge graphs, forming a heterogeneous graph index for multi-granularity retrieval. On top of this representation, a multi-agent system supports both reliable question answering and structured scientific report generation. Furthermore, we establish the IoD DeepResearch Benchmark to systematically evaluate both data representation and Deep Research capabilities in IoD scenarios. Experimental results on retrieval, QA, and report-writing tasks show that IoDResearch consistently surpasses representative RAG and Deep Research baselines. Overall, IoDResearch demonstrates the feasibility of private-data-centric Deep Research under the IoD paradigm, paving the way toward more trustworthy, reusable, and automated scientific discovery.

Problem

• Enhancing retrieval efficiency for private heterogeneous data
• Ensuring FAIR compliance in deep research frameworks
• Enabling automated scientific discovery with trustworthy data

Innovation

• Encapsulates heterogeneous resources as FAIR digital objects
• Refines data into atomic knowledge units and graphs
• Uses multi-agent system for QA and report generation