Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2510.01553 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913066430496768 |
|---|---|
| author | Shi, Zhuofan Guo, Zijie Ma, Xinjian Huang, Gang Ma, Yun Jing, Xiang |
| author_facet | Shi, Zhuofan Guo, Zijie Ma, Xinjian Huang, Gang Ma, Yun Jing, Xiang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01553 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | IoDResearch: Deep Research on Private Heterogeneous Data via the Internet of Data Shi, Zhuofan Guo, Zijie Ma, Xinjian Huang, Gang Ma, Yun Jing, Xiang Information Retrieval 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. |
| title | IoDResearch: Deep Research on Private Heterogeneous Data via the Internet of Data |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2510.01553 |