We introduce SciAtlas, a large-scale multidisciplinary academic knowledge graph that enables AI agents to move beyond keyword-based retrieval toward structured, topology-aware reasoning over scientific literature, supporting efficient and cross-disciplinary research understanding at scale.</p>\n","updatedAt":"2026-05-25T08:59:40.382Z","author":{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","fullname":"Ningyu Zhang","name":"Ningyu","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":43,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.8260862231254578},"editors":["Ningyu"],"editorAvatarUrls":["/avatars/e0fccbb2577d76088e09f054c35cffbc.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2605.22878","authors":[{"_id":"6a140eb04d9e8d8602d203bf","name":"Shuofei Qiao","hidden":false},{"_id":"6a140eb04d9e8d8602d203c0","name":"Yunxiang Wei","hidden":false},{"_id":"6a140eb04d9e8d8602d203c1","name":"Jiazheng Fan","hidden":false},{"_id":"6a140eb04d9e8d8602d203c2","name":"Bin Wu","hidden":false},{"_id":"6a140eb04d9e8d8602d203c3","name":"Busheng Zhang","hidden":false},{"_id":"6a140eb04d9e8d8602d203c4","name":"Mengru Wang","hidden":false},{"_id":"6a140eb04d9e8d8602d203c5","name":"Yuqi Zhu","hidden":false},{"_id":"6a140eb04d9e8d8602d203c6","name":"Ningyu Zhang","hidden":false},{"_id":"6a140eb04d9e8d8602d203c7","name":"Keyan Ding","hidden":false},{"_id":"6a140eb04d9e8d8602d203c8","name":"Qiang Zhang","hidden":false},{"_id":"6a140eb04d9e8d8602d203c9","name":"Huajun Chen","hidden":false}],"publishedAt":"2026-05-20T00:00:00.000Z","submittedOnDailyAt":"2026-05-25T00:00:00.000Z","title":"SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research","submittedOnDailyBy":{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","isPro":false,"fullname":"Ningyu Zhang","user":"Ningyu","type":"user","name":"Ningyu"},"summary":"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.","upvotes":30,"discussionId":"6a140eb04d9e8d8602d203ca","githubRepo":"https://github.com/zjunlp/SciAtlas","githubRepoAddedBy":"user","ai_summary":"SciAtlas presents a large-scale, multi-disciplinary knowledge graph that enables structured topological reasoning for academic research by integrating millions of papers and entities to support automated scientific discovery.","ai_keywords":["knowledge graph","academic retrieval","topological reasoning","neuro-symbolic retrieval","graph reranking","literature review","automated research trend synthesis","idea positioning","academic trajectory exploration"],"githubStars":38,"organization":{"_id":"64b1c7b70eb87fa99055af57","name":"UCL-CS","fullname":"University College London CS","avatar":"https://www.gravatar.com/avatar/f052dc0abcf2e28c2406a20bcd3df36e?d=retro&size=100"}},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"620b3bbb0668e435407c8d0a","avatarUrl":"/avatars/e0fccbb2577d76088e09f054c35cffbc.svg","isPro":false,"fullname":"Ningyu Zhang","user":"Ningyu","type":"user"},{"_id":"64bf898d979949d2e2585c9a","avatarUrl":"/avatars/da77c856ec997e2b812c06272a01c8b2.svg","isPro":false,"fullname":"mengruwang","user":"mengru","type":"user"},{"_id":"6698c1c3157ceb76c48ff996","avatarUrl":"/avatars/2f1d732c4d9df4f5b554268ee1949dda.svg","isPro":false,"fullname":"徐步强","user":"Xubqpanda","type":"user"},{"_id":"66abc6da92b9eb71fe476118","avatarUrl":"/avatars/6d1618f45cc76da80335ad926ad24552.svg","isPro":false,"fullname":"xy.r","user":"ShawnRu","type":"user"},{"_id":"688b6bac4794689f20220a32","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/3aAGGCCHesDwZjHfOQBs5.png","isPro":false,"fullname":"Zhixiang Cui","user":"Starynex","type":"user"},{"_id":"64fe84d867a8befb5c507d93","avatarUrl":"/avatars/bebdb5a75f5208c2bd187ddc560a440e.svg","isPro":false,"fullname":"3333","user":"rolnan3","type":"user"},{"_id":"64895683f534abe18eec264b","avatarUrl":"/avatars/73cc9e6db6db86793787750776b57c63.svg","isPro":false,"fullname":"Linyi Yang","user":"linyiyang2023","type":"user"},{"_id":"679e1f7c31bab0a2a309d61f","avatarUrl":"/avatars/116912ef6a154edec9d589e0e0597fc9.svg","isPro":false,"fullname":"Zhenqian","user":"ZhenqianXu","type":"user"},{"_id":"65535b54140fc44a74d43635","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/noauth/MIrD8OzDKF2aI38i7ZPjR.jpeg","isPro":false,"fullname":"Zhisong Qiu","user":"consultantQ","type":"user"},{"_id":"671e503ecb1c682e0272f2e9","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/iqcVV5VYCBcH18OdTt97n.png","isPro":false,"fullname":"chen","user":"sunnywcx","type":"user"},{"_id":"6549caee44e75a7de4fee2fa","avatarUrl":"/avatars/5aea69671eb1299aaaa948d888b4b64f.svg","isPro":false,"fullname":"Xu Ziwen","user":"xzwnlp","type":"user"},{"_id":"65d6cb9cf8729e233342ca23","avatarUrl":"/avatars/5c70f8818ea4134bb8eb6bbcbfdf071a.svg","isPro":false,"fullname":"Huxley","user":"dhao2001","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"organization":{"_id":"64b1c7b70eb87fa99055af57","name":"UCL-CS","fullname":"University College London CS","avatar":"https://www.gravatar.com/avatar/f052dc0abcf2e28c2406a20bcd3df36e?d=retro&size=100"},"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2605/2605.22878.md"}">
SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research
Authors: ,
,
,
,
,
,
,
,
,
,
Abstract
SciAtlas presents a large-scale, multi-disciplinary knowledge graph that enables structured topological reasoning for academic research by integrating millions of papers and entities to support automated scientific discovery.
AI-generated summary
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.
Community
We introduce SciAtlas, a large-scale multidisciplinary academic knowledge graph that enables AI agents to move beyond keyword-based retrieval toward structured, topology-aware reasoning over scientific literature, supporting efficient and cross-disciplinary research understanding at scale.
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2605.22878 in a model README.md to link it from this page.
Cite arxiv.org/abs/2605.22878 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2605.22878 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.