A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers Article Swipe

PDF

Mingjun Hu , Chenglong Ma , Wei Li , Wanghan Xu , Jiamin Wu , Jucheng Hu , Tianbin Li , Guohang Zhuang , Jiaqi Liu , Yingzhou Lu , Ying Chen , Chaoyang Zhang , Cheng Tan , Ying Jie , Guo–Cheng Wu , Shuo Gao , Pengcheng Chen , Jiashi Lin , Haitao Wu , Lulu Chen , Fengxiang Wang , Yuanyuan Zhang , Xiangyu Zhao , Feilong Tang , Encheng Su , Jing Ning , Xinyao Liu , Yu Du , Changkai Ji , Pengfei Jiang , Cheng Tang , Ziyan Huang , Jiyao Liu , Jiaqi Wei , Yue-Jin Yang , Xiang Zhang , Guangshuai Wang , Yang Yue , Huihui Xu , Ziyang Chen , Yizhou Wang , Chen Tang , Jianyu Wu , Yuchen Ren , Siyuan Yan , Zhonghua Wang , Zhongxing Xu , Shiyan Su , Shangquan Sun , Runkai Zhao , Zhisheng Zhang , Dingkang Yang , Jinjie Wei , Jiaqi Wang , Jin-Sen Xu , Jiangtao Yan , Wenhao Tang , Hongze Zhu , Yu Liu , Fudi Wang , Yiqing Shen , Yuanfeng Ji , Yanzhou Su , Tong Xie , Hongming Shan , Chun-Mei Feng , Zhi Bin Hou , Diping Song , Lihao Liu , Yanyan Huang , Lequan Yu , Bin Fu , Shujun Wang , X.L. Li , Xiaowei Hu , Yun Gu , Ben Fei , Benyou Wang , Y. Cao , Minjie Shen , Jie Xu , Haodong Duan , Yan Fang , Hongxia Hao , Jielan Li , Jiajun Du , Yanbo Wang , Imran Razzak , Zhongying Deng , Chi Zhang , Lijun Wu , Conghui He , Lu Zhaohui , Jinhai Huang , Wenqi Shao , Yihao Liu , Siqi Luo , Yi Xin , Xiaohong Liu , Fenghua Ling ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2508.21148

Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.

Related Topics

A Visit From St. Nicholas

C (Programming Language)

From Dusk Till Dawn

Music From Big Pink

Language

Java (Programming Language)

List Of International Cricketers From Guyana

Breton Language

From Dawn To Decadence

Jewish Exodus From The Muslim World

Dalmatian Language

The Ones Who Walk Away From Omelas

Creature From The Black Lagoon

Serbian Language

Tales From The Crypt (Tv Series)

Large Magellanic Cloud

Greetings From Asbury Park, N.J.

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2508.21148
PDF: https://arxiv.org/pdf/2508.21148
OA Status: green
OpenAlex ID: https://openalex.org/W4415987149

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415987149

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2508.21148

Digital Object Identifier
Title: A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-08-28

Full publication date if available
Authors: Mingjun Hu, Chenglong Ma, Wei Li, Wanghan Xu, Jiamin Wu, Jucheng Hu, Tianbin Li, Guohang Zhuang, Jiaqi Liu, Yingzhou Lu, Ying Chen, Chaoyang Zhang, Cheng Tan, Ying Jie, Guo–Cheng Wu, Shuo Gao, Pengcheng Chen, Jiashi Lin, Haitao Wu, Lulu Chen, Fengxiang Wang, Yuanyuan Zhang, Xiangyu Zhao, Feilong Tang, Encheng Su, Jing Ning, Xinyao Liu, Yu Du, Changkai Ji, Pengfei Jiang, Cheng Tang, Ziyan Huang, Jiyao Liu, Jiaqi Wei, Yue-Jin Yang, Xiang Zhang, Guangshuai Wang, Yang Yue, Huihui Xu, Ziyang Chen, Yizhou Wang, Chen Tang, Jianyu Wu, Yuchen Ren, Siyuan Yan, Zhonghua Wang, Zhongxing Xu, Shiyan Su, Shangquan Sun, Runkai Zhao, Zhisheng Zhang, Dingkang Yang, Jinjie Wei, Jiaqi Wang, Jin-Sen Xu, Jiangtao Yan, Wenhao Tang, Hongze Zhu, Yu Liu, Fudi Wang, Yiqing Shen, Yuanfeng Ji, Yanzhou Su, Tong Xie, Hongming Shan, Chun-Mei Feng, Zhi Bin Hou, Diping Song, Lihao Liu, Yanyan Huang, Lequan Yu, Bin Fu, Shujun Wang, X.L. Li, Xiaowei Hu, Yun Gu, Ben Fei, Benyou Wang, Y. Cao, Minjie Shen, Jie Xu, Haodong Duan, Yan Fang, Hongxia Hao, Jielan Li, Jiajun Du, Yanbo Wang, Imran Razzak, Zhongying Deng, Chi Zhang, Lijun Wu, Conghui He, Lu Zhaohui, Jinhai Huang, Wenqi Shao, Yihao Liu, Siqi Luo, Yi Xin, Xiaohong Liu, Fenghua Ling

List of authors in order
Landing page: https://arxiv.org/abs/2508.21148

Publisher landing page
PDF URL: https://arxiv.org/pdf/2508.21148

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2508.21148

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4415987149
doi	https://doi.org/10.48550/arxiv.2508.21148
ids.doi	https://doi.org/10.48550/arxiv.2508.21148
ids.openalex	https://openalex.org/W4415987149
fwci
type	preprint
title	A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2508.21148
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2508.21148
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2508.21148
locations[1].id	doi:10.48550/arxiv.2508.21148
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2508.21148
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5007932694
authorships[0].author.orcid	https://orcid.org/0000-0002-5474-6022
authorships[0].author.display_name	Mingjun Hu
authorships[0].author_position	first
authorships[0].raw_author_name	Hu, Ming
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5013612900
authorships[1].author.orcid	https://orcid.org/0000-0002-6460-7819
authorships[1].author.display_name	Chenglong Ma
authorships[1].author_position	middle
authorships[1].raw_author_name	Ma, Chenglong
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100318323
authorships[2].author.orcid	https://orcid.org/0000-0002-9438-9226
authorships[2].author.display_name	Wei Li
authorships[2].author_position	middle
authorships[2].raw_author_name	Li, Wei
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5102613788
authorships[3].author.orcid
authorships[3].author.display_name	Wanghan Xu
authorships[3].author_position	middle
authorships[3].raw_author_name	Xu, Wanghan
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5025651569
authorships[4].author.orcid	https://orcid.org/0000-0003-3479-1026
authorships[4].author.display_name	Jiamin Wu
authorships[4].author_position	middle
authorships[4].raw_author_name	Wu, Jiamin
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5103246163
authorships[5].author.orcid
authorships[5].author.display_name	Jucheng Hu
authorships[5].author_position	middle
authorships[5].raw_author_name	Hu, Jucheng
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5084901754
authorships[6].author.orcid	https://orcid.org/0000-0001-8450-5767
authorships[6].author.display_name	Tianbin Li
authorships[6].author_position	middle
authorships[6].raw_author_name	Li, Tianbin
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5081656482
authorships[7].author.orcid	https://orcid.org/0000-0002-4744-7841
authorships[7].author.display_name	Guohang Zhuang
authorships[7].author_position	middle
authorships[7].raw_author_name	Zhuang, Guohang
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5100390372
authorships[8].author.orcid	https://orcid.org/0000-0002-9775-2342
authorships[8].author.display_name	Jiaqi Liu
authorships[8].author_position	middle
authorships[8].raw_author_name	Liu, Jiaqi
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5046890926
authorships[9].author.orcid	https://orcid.org/0009-0008-7774-6018
authorships[9].author.display_name	Yingzhou Lu
authorships[9].author_position	middle
authorships[9].raw_author_name	Lu, Yingzhou
authorships[9].is_corresponding	False
authorships[10].author.id	https://openalex.org/A5100383082
authorships[10].author.orcid	https://orcid.org/0000-0002-7322-2224
authorships[10].author.display_name	Ying Chen
authorships[10].author_position	middle
authorships[10].raw_author_name	Chen, Ying
authorships[10].is_corresponding	False
authorships[11].author.id	https://openalex.org/A5100603442
authorships[11].author.orcid	https://orcid.org/0000-0001-6816-3840
authorships[11].author.display_name	Chaoyang Zhang
authorships[11].author_position	middle
authorships[11].raw_author_name	Zhang, Chaoyang
authorships[11].is_corresponding	False
authorships[12].author.id	https://openalex.org/A5100763145
authorships[12].author.orcid	https://orcid.org/0000-0002-8764-2078
authorships[12].author.display_name	Cheng Tan
authorships[12].author_position	middle
authorships[12].raw_author_name	Tan, Cheng
authorships[12].is_corresponding	False
authorships[13].author.id	https://openalex.org/A5100776906
authorships[13].author.orcid	https://orcid.org/0000-0003-2649-8241
authorships[13].author.display_name	Ying Jie
authorships[13].author_position	middle
authorships[13].raw_author_name	Ying, Jie
authorships[13].is_corresponding	False
authorships[14].author.id	https://openalex.org/A5083319940
authorships[14].author.orcid	https://orcid.org/0000-0002-1946-6770
authorships[14].author.display_name	Guo–Cheng Wu
authorships[14].author_position	middle
authorships[14].raw_author_name	Wu, Guocheng
authorships[14].is_corresponding	False
authorships[15].author.id	https://openalex.org/A5089002209
authorships[15].author.orcid	https://orcid.org/0000-0003-3096-4700
authorships[15].author.display_name	Shuo Gao
authorships[15].author_position	middle
authorships[15].raw_author_name	Gao, Shujian
authorships[15].is_corresponding	False
authorships[16].author.id	https://openalex.org/A5101979964
authorships[16].author.orcid	https://orcid.org/0000-0002-7989-0194
authorships[16].author.display_name	Pengcheng Chen
authorships[16].author_position	middle
authorships[16].raw_author_name	Chen, Pengcheng
authorships[16].is_corresponding	False
authorships[17].author.id	https://openalex.org/A5100568833
authorships[17].author.orcid	https://orcid.org/0000-0002-2696-6204
authorships[17].author.display_name	Jiashi Lin
authorships[17].author_position	middle
authorships[17].raw_author_name	Lin, Jiashi
authorships[17].is_corresponding	False
authorships[18].author.id	https://openalex.org/A5011649536
authorships[18].author.orcid	https://orcid.org/0000-0003-3458-1459
authorships[18].author.display_name	Haitao Wu
authorships[18].author_position	middle
authorships[18].raw_author_name	Wu, Haitao
authorships[18].is_corresponding	False
authorships[19].author.id	https://openalex.org/A5100420828
authorships[19].author.orcid	https://orcid.org/0000-0002-4452-045X
authorships[19].author.display_name	Lulu Chen
authorships[19].author_position	middle
authorships[19].raw_author_name	Chen, Lulu
authorships[19].is_corresponding	False
authorships[20].author.id	https://openalex.org/A5075996633
authorships[20].author.orcid	https://orcid.org/0009-0002-5267-232X
authorships[20].author.display_name	Fengxiang Wang
authorships[20].author_position	middle
authorships[20].raw_author_name	Wang, Fengxiang
authorships[20].is_corresponding	False
authorships[21].author.id	https://openalex.org/A5077518883
authorships[21].author.orcid	https://orcid.org/0000-0001-7442-6846
authorships[21].author.display_name	Yuanyuan Zhang
authorships[21].author_position	middle
authorships[21].raw_author_name	Zhang, Yuanyuan
authorships[21].is_corresponding	False
authorships[22].author.id	https://openalex.org/A5101577120
authorships[22].author.orcid	https://orcid.org/0000-0003-2538-8657
authorships[22].author.display_name	Xiangyu Zhao
authorships[22].author_position	middle
authorships[22].raw_author_name	Zhao, Xiangyu
authorships[22].is_corresponding	False
authorships[23].author.id	https://openalex.org/A5111230252
authorships[23].author.orcid
authorships[23].author.display_name	Feilong Tang
authorships[23].author_position	middle
authorships[23].raw_author_name	Tang, Feilong
authorships[23].is_corresponding	False
authorships[24].author.id	https://openalex.org/A5116867627
authorships[24].author.orcid
authorships[24].author.display_name	Encheng Su
authorships[24].author_position	middle
authorships[24].raw_author_name	Su, Encheng
authorships[24].is_corresponding	False
authorships[25].author.id	https://openalex.org/A5006858509
authorships[25].author.orcid	https://orcid.org/0000-0002-5289-331X
authorships[25].author.display_name	Jing Ning
authorships[25].author_position	middle
authorships[25].raw_author_name	Ning, Junzhi
authorships[25].is_corresponding	False
authorships[26].author.id	https://openalex.org/A5101437216
authorships[26].author.orcid	https://orcid.org/0000-0002-5948-1318
authorships[26].author.display_name	Xinyao Liu
authorships[26].author_position	middle
authorships[26].raw_author_name	Liu, Xinyao
authorships[26].is_corresponding	False
authorships[27].author.id	https://openalex.org/A5023684585
authorships[27].author.orcid	https://orcid.org/0000-0002-0868-4887
authorships[27].author.display_name	Yu Du
authorships[27].author_position	middle
authorships[27].raw_author_name	Du, Ye
authorships[27].is_corresponding	False
authorships[28].author.id	https://openalex.org/A5111097611
authorships[28].author.orcid
authorships[28].author.display_name	Changkai Ji
authorships[28].author_position	middle
authorships[28].raw_author_name	Ji, Changkai
authorships[28].is_corresponding	False
authorships[29].author.id	https://openalex.org/A5070132561
authorships[29].author.orcid	https://orcid.org/0000-0002-2975-2527
authorships[29].author.display_name	Pengfei Jiang
authorships[29].author_position	middle
authorships[29].raw_author_name	Jiang, Pengfei
authorships[29].is_corresponding	False
authorships[30].author.id	https://openalex.org/A5048286830
authorships[30].author.orcid
authorships[30].author.display_name	Cheng Tang
authorships[30].author_position	middle
authorships[30].raw_author_name	Tang, Cheng
authorships[30].is_corresponding	False
authorships[31].author.id	https://openalex.org/A5115596571
authorships[31].author.orcid
authorships[31].author.display_name	Ziyan Huang
authorships[31].author_position	middle
authorships[31].raw_author_name	Huang, Ziyan
authorships[31].is_corresponding	False
authorships[32].author.id	https://openalex.org/A5110941234
authorships[32].author.orcid
authorships[32].author.display_name	Jiyao Liu
authorships[32].author_position	middle
authorships[32].raw_author_name	Liu, Jiyao
authorships[32].is_corresponding	False
authorships[33].author.id	https://openalex.org/A5006193910
authorships[33].author.orcid	https://orcid.org/0000-0002-9927-6167
authorships[33].author.display_name	Jiaqi Wei
authorships[33].author_position	middle
authorships[33].raw_author_name	Wei, Jiaqi
authorships[33].is_corresponding	False
authorships[34].author.id	https://openalex.org/A5103698774
authorships[34].author.orcid
authorships[34].author.display_name	Yue-Jin Yang
authorships[34].author_position	middle
authorships[34].raw_author_name	Yang, Yuejin
authorships[34].is_corresponding	False
authorships[35].author.id	https://openalex.org/A5102372950
authorships[35].author.orcid	https://orcid.org/0000-0001-6706-2044
authorships[35].author.display_name	Xiang Zhang
authorships[35].author_position	middle
authorships[35].raw_author_name	Zhang, Xiang
authorships[35].is_corresponding	False
authorships[36].author.id	https://openalex.org/A5115591477
authorships[36].author.orcid
authorships[36].author.display_name	Guangshuai Wang
authorships[36].author_position	middle
authorships[36].raw_author_name	Wang, Guangshuai
authorships[36].is_corresponding	False
authorships[37].author.id	https://openalex.org/A5100636019
authorships[37].author.orcid	https://orcid.org/0000-0001-6934-2357
authorships[37].author.display_name	Yang Yue
authorships[37].author_position	middle
authorships[37].raw_author_name	Yang, Yue
authorships[37].is_corresponding	False
authorships[38].author.id	https://openalex.org/A5010287267
authorships[38].author.orcid	https://orcid.org/0000-0002-7389-4813
authorships[38].author.display_name	Huihui Xu
authorships[38].author_position	middle
authorships[38].raw_author_name	Xu, Huihui
authorships[38].is_corresponding	False
authorships[39].author.id	https://openalex.org/A5100324487
authorships[39].author.orcid	https://orcid.org/0000-0002-8564-9735
authorships[39].author.display_name	Ziyang Chen
authorships[39].author_position	middle
authorships[39].raw_author_name	Chen, Ziyang
authorships[39].is_corresponding	False
authorships[40].author.id	https://openalex.org/A5100602395
authorships[40].author.orcid	https://orcid.org/0000-0001-9888-6409
authorships[40].author.display_name	Yizhou Wang
authorships[40].author_position	middle
authorships[40].raw_author_name	Wang, Yizhou
authorships[40].is_corresponding	False
authorships[41].author.id	https://openalex.org/A5101867082
authorships[41].author.orcid	https://orcid.org/0000-0001-6830-4113
authorships[41].author.display_name	Chen Tang
authorships[41].author_position	middle
authorships[41].raw_author_name	Tang, Chen
authorships[41].is_corresponding	False
authorships[42].author.id	https://openalex.org/A5070943245
authorships[42].author.orcid	https://orcid.org/0000-0002-4590-5714
authorships[42].author.display_name	Jianyu Wu
authorships[42].author_position	middle
authorships[42].raw_author_name	Wu, Jianyu
authorships[42].is_corresponding	False
authorships[43].author.id	https://openalex.org/A5078151985
authorships[43].author.orcid	https://orcid.org/0000-0002-6009-6118
authorships[43].author.display_name	Yuchen Ren
authorships[43].author_position	middle
authorships[43].raw_author_name	Ren, Yuchen
authorships[43].is_corresponding	False
authorships[44].author.id	https://openalex.org/A5108133368
authorships[44].author.orcid
authorships[44].author.display_name	Siyuan Yan
authorships[44].author_position	middle
authorships[44].raw_author_name	Yan, Siyuan
authorships[44].is_corresponding	False
authorships[45].author.id	https://openalex.org/A5103171298
authorships[45].author.orcid	https://orcid.org/0000-0002-5550-8691
authorships[45].author.display_name	Zhonghua Wang
authorships[45].author_position	middle
authorships[45].raw_author_name	Wang, Zhonghua
authorships[45].is_corresponding	False
authorships[46].author.id	https://openalex.org/A5015118469
authorships[46].author.orcid	https://orcid.org/0000-0003-3815-7647
authorships[46].author.display_name	Zhongxing Xu
authorships[46].author_position	middle
authorships[46].raw_author_name	Xu, Zhongxing
authorships[46].is_corresponding	False
authorships[47].author.id	https://openalex.org/A5037350701
authorships[47].author.orcid	https://orcid.org/0009-0000-5486-8591
authorships[47].author.display_name	Shiyan Su
authorships[47].author_position	middle
authorships[47].raw_author_name	Su, Shiyan
authorships[47].is_corresponding	False
authorships[48].author.id	https://openalex.org/A5103056828
authorships[48].author.orcid	https://orcid.org/0000-0002-6292-2495
authorships[48].author.display_name	Shangquan Sun
authorships[48].author_position	middle
authorships[48].raw_author_name	Sun, Shangquan
authorships[48].is_corresponding	False
authorships[49].author.id	https://openalex.org/A5040777365
authorships[49].author.orcid	https://orcid.org/0000-0002-3649-9902
authorships[49].author.display_name	Runkai Zhao
authorships[49].author_position	middle
authorships[49].raw_author_name	Zhao, Runkai
authorships[49].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2508.21148
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers
has_fulltext	False
is_retracted	False
updated_date	2025-11-08T23:21:52.890332
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2508.21148
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2508.21148
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2508.21148
primary_location.id	pmh:oai:arXiv.org:2508.21148
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2508.21148
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2508.21148
publication_date	2025-08-28
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	32, 43, 54, 61, 139, 177, 195, 204, 218
abstract_inverted_index.--	114
abstract_inverted_index.On	129
abstract_inverted_index.We	52, 84
abstract_inverted_index.an	100
abstract_inverted_index.as	42, 217
abstract_inverted_index.by	22
abstract_inverted_index.in	14, 159, 221
abstract_inverted_index.is	9, 20
abstract_inverted_index.of	26, 40, 57, 64, 103
abstract_inverted_index.on	187
abstract_inverted_index.to	92, 194
abstract_inverted_index.we	131, 175
abstract_inverted_index.190	134
abstract_inverted_index.270	105
abstract_inverted_index.and	12, 47, 60, 71, 125, 137, 146, 163, 171, 192
abstract_inverted_index.are	5
abstract_inverted_index.for	206
abstract_inverted_index.how	7
abstract_inverted_index.the	23, 38, 68
abstract_inverted_index.why	109
abstract_inverted_index.yet	17
abstract_inverted_index.(AI)	213
abstract_inverted_index.This	29
abstract_inverted_index.data	50, 59, 161
abstract_inverted_index.from	78, 89, 141
abstract_inverted_index.over	104, 133
abstract_inverted_index.pose	111
abstract_inverted_index.that	36, 74, 119, 215
abstract_inverted_index.this	201
abstract_inverted_index.true	219
abstract_inverted_index.with	149
abstract_inverted_index.work	202
abstract_inverted_index.Large	1
abstract_inverted_index.These	153
abstract_inverted_index.base.	199
abstract_inverted_index.based	186
abstract_inverted_index.data.	28
abstract_inverted_index.exams	143
abstract_inverted_index.model	63
abstract_inverted_index.shift	140, 179
abstract_inverted_index.their	18, 48
abstract_inverted_index.trace	138
abstract_inverted_index.where	183
abstract_inverted_index.Models	3
abstract_inverted_index.across	95
abstract_inverted_index.agents	185
abstract_inverted_index.domain	123
abstract_inverted_index.expert	172
abstract_inverted_index.issues	158
abstract_inverted_index.models	46, 94
abstract_inverted_index.nature	25
abstract_inverted_index.recent	87
abstract_inverted_index.review	86
abstract_inverted_index.shaped	21
abstract_inverted_index.static	142
abstract_inverted_index.survey	30
abstract_inverted_index.toward	144, 180
abstract_inverted_index.applied	13
abstract_inverted_index.between	45
abstract_inverted_index.complex	24
abstract_inverted_index.corpora	77, 118
abstract_inverted_index.demands	113
abstract_inverted_index.discuss	164
abstract_inverted_index.diverse	96
abstract_inverted_index.examine	132
abstract_inverted_index.general	79
abstract_inverted_index.living,	196
abstract_inverted_index.natural	80
abstract_inverted_index.outline	176
abstract_inverted_index.partner	220
abstract_inverted_index.require	120
abstract_inverted_index.roadmap	205
abstract_inverted_index.showing	108
abstract_inverted_index.systems	182, 214
abstract_inverted_index.unified	55
abstract_inverted_index.Finally,	174
abstract_inverted_index.Language	2
abstract_inverted_index.Sci-LLMs	41, 110, 188
abstract_inverted_index.actively	189
abstract_inverted_index.advanced	150
abstract_inverted_index.analyses	155
abstract_inverted_index.analysis	102
abstract_inverted_index.building	207
abstract_inverted_index.datasets	136
abstract_inverted_index.distinct	112
abstract_inverted_index.emerging	165
abstract_inverted_index.enabling	126
abstract_inverted_index.evolving	197, 210
abstract_inverted_index.function	216
abstract_inverted_index.language	81
abstract_inverted_index.paradigm	178
abstract_inverted_index.presents	31
abstract_inverted_index.process-	145
abstract_inverted_index.progress	19
abstract_inverted_index.provides	203
abstract_inverted_index.reframes	37
abstract_inverted_index.taxonomy	56
abstract_inverted_index.Sci-LLMs,	88
abstract_inverted_index.alongside	99
abstract_inverted_index.benchmark	135
abstract_inverted_index.datasets,	107
abstract_inverted_index.datasets.	83
abstract_inverted_index.extensive	101
abstract_inverted_index.formulate	53
abstract_inverted_index.highlight	156
abstract_inverted_index.involving	167
abstract_inverted_index.knowledge	8, 198
abstract_inverted_index.pipelines	170
abstract_inverted_index.research,	16
abstract_inverted_index.solutions	166
abstract_inverted_index.synthesis	35
abstract_inverted_index.validate,	191
abstract_inverted_index.(Sci-LLMs)	4
abstract_inverted_index.Scientific	0
abstract_inverted_index.annotation	169
abstract_inverted_index.artificial	211
abstract_inverted_index.autonomous	184
abstract_inverted_index.challenges	73
abstract_inverted_index.contribute	193
abstract_inverted_index.discovery.	224
abstract_inverted_index.evaluation	151
abstract_inverted_index.invariance	124
abstract_inverted_index.knowledge,	66
abstract_inverted_index.persistent	157
abstract_inverted_index.preserving	122
abstract_inverted_index.processing	82
abstract_inverted_index.protocols.	152
abstract_inverted_index.reasoning.	128
abstract_inverted_index.scientific	15, 27, 58, 65, 76, 97, 160, 223
abstract_inverted_index.substrate.	51
abstract_inverted_index.underlying	49
abstract_inverted_index.assessments	148
abstract_inverted_index.closed-loop	181
abstract_inverted_index.continually	209
abstract_inverted_index.cross-modal	127
abstract_inverted_index.development	39, 162
abstract_inverted_index.emphasizing	67
abstract_inverted_index.evaluation,	130
abstract_inverted_index.experiment,	190
abstract_inverted_index.foundations	91
abstract_inverted_index.integrated,	11
abstract_inverted_index.multimodal,	69
abstract_inverted_index.specialized	93
abstract_inverted_index.validation.	173
abstract_inverted_index.accelerating	222
abstract_inverted_index.co-evolution	44
abstract_inverted_index.cross-scale,	70
abstract_inverted_index.data-centric	34, 154
abstract_inverted_index.disciplines,	98
abstract_inverted_index.hierarchical	62
abstract_inverted_index.intelligence	212
abstract_inverted_index.multi-scale,	116
abstract_inverted_index.represented,	10
abstract_inverted_index.transforming	6
abstract_inverted_index.trustworthy,	208
abstract_inverted_index.Collectively,	200
abstract_inverted_index.differentiate	75
abstract_inverted_index.comprehensive,	33
abstract_inverted_index.heterogeneous,	115
abstract_inverted_index.semi-automated	168
abstract_inverted_index.systematically	85
abstract_inverted_index.domain-specific	72
abstract_inverted_index.general-purpose	90
abstract_inverted_index.representations	121
abstract_inverted_index.uncertainty-laden	117
abstract_inverted_index.discovery-oriented	147
abstract_inverted_index.pre-/post-training	106
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	120
citation_normalized_percentile