SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qiao, Shuofei, Wei, Yunxiang, Fan, Jiazheng, Wu, Bin, Zhang, Busheng, Wang, Mengru, Zhu, Yuqi, Zhang, Ningyu, Ding, Keyan, Zhang, Qiang, Chen, Huajun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916037779259392
author Qiao, Shuofei
Wei, Yunxiang
Fan, Jiazheng
Wu, Bin
Zhang, Busheng
Wang, Mengru
Zhu, Yuqi
Zhang, Ningyu
Ding, Keyan
Zhang, Qiang
Chen, Huajun
author_facet Qiao, Shuofei
Wei, Yunxiang
Fan, Jiazheng
Wu, Bin
Zhang, Busheng
Wang, Mengru
Zhu, Yuqi
Zhang, Ningyu
Ding, Keyan
Zhang, Qiang
Chen, Huajun
contents The exponential growth of global academic output has confronted researchers and AI agents with an unprecedented ``information explosion,'' where fragmented and unstructured knowledge organization impedes deep interdisciplinary integration. Current academic retrieval tools predominantly rely on superficial keyword matching or vector-space semantic retrieval, which lack the topological reasoning capabilities required to navigate complex logical connections. Agentic deep-research-based frameworks are often prone to logical hallucinations and consuming high inference costs. To bridge this gap, in this report, we introduce SciAtlas, a large-scale, multi-disciplinary, heterogeneous academic resource knowledge graph designed as a panoramic scientific evolution network. By integrating over 43M papers from 26 disciplines, and a total of 157M entities and 3B triplets, SciAtlas provides a structured topological cognitive substrate that dismantles disciplinary barriers and furnishes AI agents with a global perspective. Furthermore, we develop a neuro-symbolic retrieval algorithm featuring tri-path collaborative recall and graph reranking, achieving a seamless transition from simple semantic matching to deterministic association discovery. We also present key application directions of SciAtlas, including literature review, automated research trend synthesis, idea positioning, and academic trajectory exploration, to demonstrate that SciAtlas can serve as an effective ``cognitive map'' to empower the full loop of automated scientific research while significantly reducing reasoning costs. We have released the interfaces for KG retrieval and various downstream tasks in our GitHub repo.
format Preprint
id arxiv_https___arxiv_org_abs_2605_22878
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
Qiao, Shuofei
Wei, Yunxiang
Fan, Jiazheng
Wu, Bin
Zhang, Busheng
Wang, Mengru
Zhu, Yuqi
Zhang, Ningyu
Ding, Keyan
Zhang, Qiang
Chen, Huajun
Artificial Intelligence
Computation and Language
Information Retrieval
Machine Learning
The exponential growth of global academic output has confronted researchers and AI agents with an unprecedented ``information explosion,'' where fragmented and unstructured knowledge organization impedes deep interdisciplinary integration. Current academic retrieval tools predominantly rely on superficial keyword matching or vector-space semantic retrieval, which lack the topological reasoning capabilities required to navigate complex logical connections. Agentic deep-research-based frameworks are often prone to logical hallucinations and consuming high inference costs. To bridge this gap, in this report, we introduce SciAtlas, a large-scale, multi-disciplinary, heterogeneous academic resource knowledge graph designed as a panoramic scientific evolution network. By integrating over 43M papers from 26 disciplines, and a total of 157M entities and 3B triplets, SciAtlas provides a structured topological cognitive substrate that dismantles disciplinary barriers and furnishes AI agents with a global perspective. Furthermore, we develop a neuro-symbolic retrieval algorithm featuring tri-path collaborative recall and graph reranking, achieving a seamless transition from simple semantic matching to deterministic association discovery. We also present key application directions of SciAtlas, including literature review, automated research trend synthesis, idea positioning, and academic trajectory exploration, to demonstrate that SciAtlas can serve as an effective ``cognitive map'' to empower the full loop of automated scientific research while significantly reducing reasoning costs. We have released the interfaces for KG retrieval and various downstream tasks in our GitHub repo.
title SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
topic Artificial Intelligence
Computation and Language
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2605.22878