Article(id=1329419588833489818, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1329419577676641015, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202550223, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1742745600000, receivedDateStr=2025-03-24, revisedDate=1768752000000, revisedDateStr=2026-01-19, acceptedDate=1769616000000, acceptedDateStr=2026-01-29, onlineDate=1794887929399, onlineDateStr=2026-11-17, pubDate=1777564800000, pubDateStr=2026-05-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794887929399, onlineIssueDateStr=2026-11-17, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794887929399, creator=13701087609, updateTime=1794887929399, updator=13701087609, issue=Issue{id=1329419577676641015, tenantId=1146029695717560320, journalId=1324759914146529478, year='2026', volume='63', issue='5', pageStart='1095', pageEnd='1375', issueExtLink='null', onlineDate='null', pubDate='1777564800000', pubDateStr='2026-05-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794887926739, creator='13701087609', updateTime=1794887926739, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext=null, issueFiles=null, downloadFileDto=null}, startPage=1305, endPage=1318, ext={EN=ArticleExt(id=1329419589068370844, articleId=1329419588833489818, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=AI-Model Network: Concept, Current State and Future, columnId=1329419589001261979, journalTitle=Journal of Computer Research and Development, columnName=Network Technology, runingTitle=null, highlight=null, articleAbstract=

While the primary function of computers lies in computation and processing, the core value of the Internet is rooted in sharing and collaboration. Computers create the Internet, and the Internet empowers the value of computers. The rapid development of the Internet, cloud computing, and big data is pushing artificial intelligence into the era of large models (LMs). However, the practical application of LMs is currently hindered by high training costs and deployment complexities, driving a shift toward lightweight, private, and domain-specific models. With the rapid proliferation and wide distribution of heterogeneous models, enabling effective interaction and collaboration among them has emerged as a critical bottleneck that urgently needs to be addressed in LM development. Drawing inspiration from the development of the Internet, we propose the concept, vision, and system architecture of world wide AI-model network (AI-ModelNet). It is a novel paradigm that achieves interconnection, capability sharing, and collaborative reasoning by establishing pathways between models. We first briefly review the current state of single-model and multi-model research. Subsequently, the systemic vision and hierarchical architecture of AI-ModelNet are articulated, followed by validation of the framework’s feasibility through a prototype system and diverse application cases. Finally, key directions for future research are discussed preliminarily.

, authors=Zhetao Li, Xiyu Zeng, Jianhui Wang, Yong Xiao, Zhongren Liu, Junru Wu, Junjie Lai, Jijun Huang, Saiqin Long, authorsList=Zhetao Li, Xiyu Zeng, Jianhui Wang, Yong Xiao, Zhongren Liu, Junru Wu, Junjie Lai, Jijun Huang, Saiqin Long, authorCompany=null, correspAuthors=null, authorNote=

born in 1980. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent network and artificial intelligence

born in 1999. PhD candidate. Her main research interests include data privacy and artificial intelligence

born in 1997. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

born in 1996. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

born in 2001. Master candidate. His main research interests include large language models and natural language processing

born in 2000. Master candidate. His main research interests include large language models and cybersecurity

born in 1986. PhD, professor, PhD supervisor. Member of CCF. Her main research interest includes edge computing

, correspAuthorsNote=null, copyrightStatement=Copyright © 2026 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1329419591681422270, articleId=1329419588833489818, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=模型互联网:概念、现状和未来, columnId=1329419589143868317, journalTitle=计算机研究与发展, columnName=网络技术, runingTitle=null, highlight=null, articleAbstract=

计算机的主要功能在于计算与处理,互联网的价值在于共享与协作。计算机催生互联网,互联网放大计算机的价值。互联网、云计算与大数据的快速发展推动了人工智能迈入大模型时代。然而,大模型在实际应用中面临训练成本高昂、泛在部署困难等挑战,促使大模型朝轻量化、私有化及垂直化方向发展。随着异构模型的急速增长和广泛分布,模型间的交互协同成为大模型发展亟须突破的瓶颈问题。受计算机互联网的发展模式启发,提出模型互联网(AI-ModelNet)的概念、构想及系统架构,它是一种通过构建模型间通路,实现互联互通、能力共享与协同推理等的新范式。首先,简要介绍了单一模型与多模型场景的发展现状;然后,系统性地阐述了模型互联网的总体构想与层次结构,并结合原型系统与相关应用实例验证了其可行性与实用性;最后,初步展望了未来研究的主要方向。

, authors=李哲涛, 曾曦玉, 王建辉, 肖勇, 刘忠仁, 吴俊儒, 赖俊杰, 黄纪俊, 龙赛琴, authorsList=李哲涛, 曾曦玉, 王建辉, 肖勇, 刘忠仁, 吴俊儒, 赖俊杰, 黄纪俊, 龙赛琴, authorCompany=null, correspAuthors=null, authorNote=

1980年生。博士,教授,博士生导师。CCF会员。主要研究方向为智能网络、人工智能

1999年生。博士研究生。主要研究方向为数据隐私、人工智能

1997年生。博士研究生。主要研究方向为移动边缘计算、人工智能

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

1996年生。博士研究生。主要研究方向为移动边缘计算、人工智能

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

2001年生。硕士研究生。主要研究方向为大模型、自然语言处理

2000年生。硕士研究生。主要研究方向为大模型、网络安全

1986年生。博士,教授,博士生导师。CCF会员。主要研究方向为边缘计算

, correspAuthorsNote=null, copyrightStatement=版权所有 © 2026 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=o14KkenL0TxUlnkAcovLSA==, magXml=EjFOqI1l2XP0rEkdv7R/vQ==, pdfUrl=null, pdf=sNTcFj2oVHsAU0u+QkP/Pg==, pdfFileSize=3683966, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=jVI0LGd4MMgAyT88bxyVVg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=h6OlgT0Q7xivBQ4FCcfTSA==, mapNumber=null, fund=null)}, authors=[Author(id=1329419591987606467, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liztchina@hotmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592088269765, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419591987606467, language=EN, stringName=Zhetao Li, firstName=Zhetao, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1980. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent network and artificial intelligence

"}, bioImg=null, bioContent=

born in 1980. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent network and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592193127366, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419591987606467, language=CN, stringName=李哲涛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"NGdjkywb3qvUT3z4kAWR1Q==","content":"

1980年生。博士,教授,博士生导师。CCF会员。主要研究方向为智能网络、人工智能

"}, bioImg=NGdjkywb3qvUT3z4kAWR1Q==, bioContent=

1980年生。博士,教授,博士生导师。CCF会员。主要研究方向为智能网络、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419592272819144, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592344122314, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592272819144, language=EN, stringName=Xiyu Zeng, firstName=Xiyu, middleName=null, lastName=Zeng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1999. PhD candidate. Her main research interests include data privacy and artificial intelligence

"}, bioImg=null, bioContent=

born in 1999. PhD candidate. Her main research interests include data privacy and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592407036875, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592272819144, language=CN, stringName=曾曦玉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"ThuA7iI4JM5xMkW0AtHHBQ==","content":"

1999年生。博士研究生。主要研究方向为数据隐私、人工智能

"}, bioImg=ThuA7iI4JM5xMkW0AtHHBQ==, bioContent=

1999年生。博士研究生。主要研究方向为数据隐私、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419592465757133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592545448911, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592465757133, language=EN, stringName=Jianhui Wang, firstName=Jianhui, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1997. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

"}, bioImg=null, bioContent=

born in 1997. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592616752080, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592465757133, language=CN, stringName=王建辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"T6lRGdIWl0ynNHygDmhhzw==","content":"

1997年生。博士研究生。主要研究方向为移动边缘计算、人工智能

"}, bioImg=T6lRGdIWl0ynNHygDmhhzw==, bioContent=

1997年生。博士研究生。主要研究方向为移动边缘计算、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419592683860946, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592738386900, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592683860946, language=EN, stringName=Yong Xiao, firstName=Yong, middleName=null, lastName=Xiao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

"}, bioImg=null, bioContent=

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592797107157, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592683860946, language=CN, stringName=肖勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"XESCVxqMbkWchxx2waZuxQ==","content":"

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

"}, bioImg=XESCVxqMbkWchxx2waZuxQ==, bioContent=

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419592851633111, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592927130585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592851633111, language=EN, stringName=Zhongren Liu, firstName=Zhongren, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1996. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

"}, bioImg=null, bioContent=

born in 1996. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592985850842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592851633111, language=CN, stringName=刘忠仁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"j3yRPyRoQ6sUj5BXLMRmlw==","content":"

1996年生。博士研究生。主要研究方向为移动边缘计算、人工智能

"}, bioImg=j3yRPyRoQ6sUj5BXLMRmlw==, bioContent=

1996年生。博士研究生。主要研究方向为移动边缘计算、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419593069736924, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419593145234398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593069736924, language=EN, stringName=Junru Wu, firstName=Junru, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

"}, bioImg=null, bioContent=

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419593220731871, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593069736924, language=CN, stringName=吴俊儒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"Sybl90+Fgjtf1ETSqKgGWA==","content":"

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

"}, bioImg=Sybl90+Fgjtf1ETSqKgGWA==, bioContent=

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419593279452129, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419593359143907, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593279452129, language=EN, stringName=Junjie Lai, firstName=Junjie, middleName=null, lastName=Lai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 2001. Master candidate. His main research interests include large language models and natural language processing

"}, bioImg=null, bioContent=

born in 2001. Master candidate. His main research interests include large language models and natural language processing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419593464001508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593279452129, language=CN, stringName=赖俊杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"3+jwjjn5LpZy/4GU9oaVVw==","content":"

2001年生。硕士研究生。主要研究方向为大模型、自然语言处理

"}, bioImg=3+jwjjn5LpZy/4GU9oaVVw==, bioContent=

2001年生。硕士研究生。主要研究方向为大模型、自然语言处理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419593543693286, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419593623385064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593543693286, language=EN, stringName=Jijun Huang, firstName=Jijun, middleName=null, lastName=Huang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 2000. Master candidate. His main research interests include large language models and cybersecurity

"}, bioImg=null, bioContent=

born in 2000. Master candidate. His main research interests include large language models and cybersecurity

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419593715659753, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593543693286, language=CN, stringName=黄纪俊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"dtEKWFPoTbbTFxFAjiPSig==","content":"

2000年生。硕士研究生。主要研究方向为大模型、网络安全

"}, bioImg=dtEKWFPoTbbTFxFAjiPSig==, bioContent=

2000年生。硕士研究生。主要研究方向为大模型、网络安全

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419593778574315, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=8, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419593858266093, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593778574315, language=EN, stringName=Saiqin Long, firstName=Saiqin, middleName=null, lastName=Long, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1986. PhD, professor, PhD supervisor. Member of CCF. Her main research interest includes edge computing

"}, bioImg=null, bioContent=

born in 1986. PhD, professor, PhD supervisor. Member of CCF. Her main research interest includes edge computing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419593929569262, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593778574315, language=CN, stringName=龙赛琴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"YZJpbak8BByViLYiEywJKQ==","content":"

1986年生。博士,教授,博士生导师。CCF会员。主要研究方向为边缘计算

"}, bioImg=YZJpbak8BByViLYiEywJKQ==, bioContent=

1986年生。博士,教授,博士生导师。CCF会员。主要研究方向为边缘计算

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])])], keywords=[Keyword(id=1329419594030232559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, orderNo=1, keyword=large models), Keyword(id=1329419594088952816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, orderNo=2, keyword=multi-model collaboration), Keyword(id=1329419594151867377, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, orderNo=3, keyword=model interaction), Keyword(id=1329419594223170546, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, orderNo=4, keyword=AI- model network), Keyword(id=1329419594290279411, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, orderNo=5, keyword=the Internet), Keyword(id=1329419594348999668, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, orderNo=1, keyword=大模型), Keyword(id=1329419594416108533, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, orderNo=2, keyword=多模型协作), Keyword(id=1329419594479023094, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, orderNo=3, keyword=模型交互), Keyword(id=1329419594554520567, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, orderNo=4, keyword=模型互联网), Keyword(id=1329419594630018040, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, orderNo=5, keyword=互联网)], refs=[Reference(id=1329419596001554440, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=Berners-Lee T, Cailliau R, Luotonen A, et al. The world-wide web[J]. Communications of the ACM, 1994, 37(8): 76−82, articleTitle=null, refAbstract=null), Reference(id=1329419596102217737, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [C] // Proc of the 31st Conf on Neural Information Processing Systems. New York: ACM, 2017: 6000–6010, articleTitle=null, refAbstract=null), Reference(id=1329419596165132298, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Lin Luyuan, Wang Lingzhi, Guo Jinsong, et al. Investigating bias in LLM-based bias detection: Disparities between LLMs and human perception [C] //Proc of the 31st Int Conf on Computational Linguistics. Stroudsburg, PA: ACL, 2025: 10634−10649, articleTitle=null, refAbstract=null), Reference(id=1329419596236435467, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=苏金树. 领域定制方法促进网络与计算发展的思考[J]. 计算机研究与发展, 2025, 62(12): 2889−2894, articleTitle=null, refAbstract=null), Reference(id=1329419596332904460, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Su Jinshu. Thinking on networking and computing promoted by domain-specific method[J]. Journal of Computer Research and Development, 2025, 62(12): 2889−2894 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419596420984845, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Shagbin, Shi Weijia, Wang Yike, et al. Don’t hallucinate, abstain: Identifying LLM knowledge gaps via multi-LLM collaboration [C] //Proc of the 62nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2024: 14664−14690, articleTitle=null, refAbstract=null), Reference(id=1329419596496482318, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Zhicong, Li Jin, Li Peiguang, et al. Rethinking the reversal curse of LLMs: A prescription from human knowledge reversal [C] //Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 7518−7530, articleTitle=null, refAbstract=null), Reference(id=1329419596559396879, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Weizhou, Li Chenliang, Chen Hongzhan, et al. Small LLMs are weak tool learners: A multi-LLM agent [C] //Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 16658−16680, articleTitle=null, refAbstract=null), Reference(id=1329419596613922832, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Qitian J, Bieker J, Li Xiuyu, et al. ROUTERBENCH: A benchmark for multi-LLM routing system [J]. arXiv preprint, arXiv: 2403.12031, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419596676837393, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Agrawal A, Aralikatti R, Satheesh A, et al. Uncertainty-aware answer selection for improved reasoning in multi-LLM systems [C] //Proc of the Findings of the Association for Computational Linguistics (EMNLP 2025). Stroudsburg, PA: ACL, 2025: 25090−25098, articleTitle=null, refAbstract=null), Reference(id=1329419596752334866, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Tang Liyan, Laban P, Durrett G. MiniCheck: Efficient fact-checking of LLMs on grounding documents[C]// Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 8818–8847, articleTitle=null, refAbstract=null), Reference(id=1329419596819443731, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong jing. China home to over one-third of world’s AI large language models [N/OL]. China Daily. (2024-07-03)[2026-01-01]. https://language.chinadaily.com.cn/a/202407/03/WS66850bcda31095c51c50c29e.html, articleTitle=null, refAbstract=null), Reference(id=1329419596886552596, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong jing. China home to over one-third of world’s AI large language models [N/OL]. China Daily. (2024-07-03)[2026-01-01]. https://language.chinadaily.com.cn/a/202407/03/WS66850bcda31095c51c50c29e.html, articleTitle=null, refAbstract=null), Reference(id=1329419596945272853, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=He Na, Yan Yinging, Wu Ziyang, et al. Chat GPT-4 significantly surpasses GPT-3.5 in drug information queries[J]. Journal of Telemedicine and Telecare, 2025, 31(2): 306−308, articleTitle=null, refAbstract=null), Reference(id=1329419597008187414, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Akhiad B, Itay L, Izik G, et al. Llama-nemotron: Efficient reasoning models [J]. arXiv preprint arXiv: 2505.00949, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419597071101975, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Deng Zehang, Ma Wanlun, Han Qinglong, et al. Exploring DeepSeek: A survey on advances, applications, challenges and future directions[J]. IEEE/CAA Journal of Automatica Sinica, 2025, 12(5): 872−893, articleTitle=null, refAbstract=null), Reference(id=1329419597134016536, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Bai Shuai, Chen Keqin, Liu Xuejing, et al. Qwen2.5-vl technical report[J]. arXiv preprint arXiv: 2502.13923, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419597192736793, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Team Kimi, Du Angang, Yin Boohong, et al. Kimi-vl technical report[J]. arXiv preprint arXiv: 2504.07491, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419597255651354, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Aiersilan A, Liu Mingzhe. LLM-enhanced traffic editor for accelerated testing of autonomous vehicles under various pedestrian behaviors[C]//Proc of the 5th Int Conf on Smart Transportation and City Engineering. Bellingham, WA: SPIE, 2025, 13575: 1054−1060, articleTitle=null, refAbstract=null), Reference(id=1329419597318565915, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Guan Yanchu, Wang Dong, Chu Zhixuan, et al. Intelligent agents with LLM-based process automation[C]// Proc of the 30th ACM SIGKDD Conf on Knowledge Discovery and Data Mining. New York: ACM, 2024: 5018−5027, articleTitle=null, refAbstract=null), Reference(id=1329419597373091868, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Shican, Ma Xiao, Luo Dehui, et al. Automated literature research and review-generation method based on large language models[J]. National Science Review, 2025, 12(6): nwaf169, articleTitle=null, refAbstract=null), Reference(id=1329419597436006429, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Derong, Zhang Ziheng, Zhu Zhihong, et al. Mitigating hallucinations of large language models in medical information extraction via contrastive decoding[C]// Proc of the Findings of the Association for Computational Linguistics (EMNLP 2024). Stroudsburg, PA: ACL, 2024: 7744−7757, articleTitle=null, refAbstract=null), Reference(id=1329419597494726686, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Ma Mulei, Gong Chenyu, Zeng Liekang, et al. Multi-tier multi-node scheduling of LLM for collaborative AI computing[C]// Proc of the 2025 IEEE Conf on Computer Communications (IEEE INFOCOM 2025). Piscataway, NJ: IEEE, 2025: 1−10, articleTitle=null, refAbstract=null), Reference(id=1329419597553446943, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Jinliang, Pang Ziliang, Xiao Min, et al. Merge, ensemble, and cooperate! a survey on collaborative strategies in the era of large language models[J]. arXiv preprint arXiv: 2407.06089, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419597616361504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Yadav P, Tam D, Choshen L, et al. Ties-Merging: Resolving interference when merging models[J]. Advances in Neural Information Processing Systems, 2023, 36: 7093−7115, articleTitle=null, refAbstract=null), Reference(id=1329419597666693153, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Zheyi, Fan Chenghao, Wei Wei, et al. Twin-Merging: Dynamic integration of modular expertise in model merging[J]. Advances in Neural Information Processing Systems, 2024, 37: 78905−78935, articleTitle=null, refAbstract=null), Reference(id=1329419597721219106, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yichong, Feng Xiaocheng, Li Baohang, et al. Ensemble learning for heterogeneous large language models with deep parallel collaboration[J]. Advances in Neural Information Processing Systems, 2024, 37: 119838−119860, articleTitle=null, refAbstract=null), Reference(id=1329419597788327971, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=王建辉, 李哲涛, 伍涛, 等. Token级多模型并联协作推理[J]. 计算机学报, 2025, 48(11): 2579−2593, articleTitle=null, refAbstract=null), Reference(id=1329419597855436836, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jianhui, Li Zhetao, Wu Tao, et al. Token-level collaborative reasoning for parallel multi-models[J]. Chinese Journal of Computers, 2025, 48(11): 2579−2593 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419597914157093, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=吴俊儒, 李哲涛, 王建辉, 等. 基于协作关系的模型动态路由. [J/OL]. 软件学报, 2025[2026-01-02]. http: //www.jos.org.cn/1000-9825/7498.html, articleTitle=null, refAbstract=null), Reference(id=1329419597972877350, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Junru, Li Zhetao, Wang Jianhui, et al. Dynamic model routing based on collaborative relationship [J/OL]. Journal of Software, 2025[2026-01-02]. http://www.jos.org.cn/1000-9825/7498.html (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1329419598056763431, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Pan Shirui, Luo Linhao, Wang Yufei, et al. Unifying large language models and knowledge graphs: A roadmap[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3580−3599, articleTitle=null, refAbstract=null), Reference(id=1329419598115483688, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Weiqi, Wu Hongqiu, Jiang Lai, et al. From role-play to drama-interaction: An LLM solution [C]// Proc of the Findings of the Association for Computational Linguistics (ACL 2024 ). Stroudsburg, PA: ACL, 2024: 3271−3290, articleTitle=null, refAbstract=null), Reference(id=1329419598174203945, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Ong I, Almahairi A, Wu V, et al. RouteLLM: Learning to route LLMs with preference data[J]. arXiv preprint arXiv: 2406.18665, 2024, articleTitle=null, refAbstract=null), Reference(id=1329419598241312810, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Ding Dujian, Mallick A, Zhang Shaokun, et al. BEST-Route: Adaptive LLM routing with test-time optimal compute[C/OL]// Proc of the 42nd Int Conf on Machine Learning. New York: ACM, 2025[2026-01-03]. https://openreview.net/forum?id=tFBIbCVXkG, articleTitle=null, refAbstract=null), Reference(id=1329419598295838763, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Tao, Shen Yanzhen, You Jiaxuan. GraphRouter: A graph-based router for LLM selections[C/OL]// Proc of the 13th Int Conf on Learning Representations. New York: ACM, 2025[2026-01-03]. https://openreview.net/forum?id=eU39PDsZtT, articleTitle=null, refAbstract=null), Reference(id=1329419598362947629, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Jun, Kong Zhenglun, Yang Changdi, et al. RCR-Router: Efficient role-aware context routing for multi-agent LLM systems with structured memory[J]. arXiv preprint, arXiv: 2508.04903, 2025, articleTitle=null, refAbstract=null), Reference(id=1329419598446833710, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Stripelis D, Xu Zhaozhou, Hu Zijian, et al. TensorOpera router: A multi-model router for efficient LLM inference[C]// Proc of the 2024 Conf on Empirical Methods in Natural Language Processing (EMNLP 2024). Stroudsburg, PA: ACL, 2024: 452−462, articleTitle=null, refAbstract=null), Reference(id=1329419598513942575, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Yilun, Li Shuang, Torralba A, et al. Improving factuality and reasoning in language models through multiagent debate[C]//Proc of the 41st Int Conf on Machine Learning. New York: ACM, 2024: 11733−11763, articleTitle=null, refAbstract=null), Reference(id=1329419598572662833, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Yuzhen, Bai Yuzhou, Zhu Zhihao, et al. C-Eval: A multi-level multi-discipline Chinese evaluation suite for foundation models [C]// Proc of the 37th Conf on Neural Information Processing Systems (NeurIPS 2023). New York: ACM, 2023: 62991−63010, articleTitle=null, refAbstract=null), Reference(id=1329419598622994482, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Clark C, Lee K, Chang Mingwei, et al. BoolQ: Exploring the surprising difficulty of natural yes/no questions[C]// Proc of the 2019 Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: ACL, 2019: 2924−2936, articleTitle=null, refAbstract=null), Reference(id=1329419598685909043, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Hendrycks D, Burns C, Basart S, et al. Measuring massive multitask language understanding[J]. arXiv preprint arXiv: 2009.03300, 2020, articleTitle=null, refAbstract=null), Reference(id=1329419598753017908, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Song Wei, Huang Zhenya, Cheng Cheng, et al. IRT-Router: Effective and interpretable multi-LLM routing via item response theory[C]// Proc of the 63rd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2025: 15629−15644, articleTitle=null, refAbstract=null), Reference(id=1329419598828515381, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Zhaoxuan, Zhou Zijian, Verma1 A, et al. TETRIS: Optimal draft token selection for batch speculative decoding. [C]// Proc of the 63rd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2025: 33329−33345, articleTitle=null, refAbstract=null), Reference(id=1329419598891429942, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Rao S, Philip S. Announcing the agent2agent protocol (A2A)[EB/OL]. 2025[2025-10-19]. https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/, articleTitle=null, refAbstract=null), Reference(id=1329419598941761591, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Yuhan, Song Zirui, Zhang Juntian, et al. The stepwise deception: Simulating the evolution from true news to fake news with LLM agents[C]// Proc of the 2025 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2025: 26187−26203, articleTitle=null, refAbstract=null), Reference(id=1329419598996287544, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=Yu Miao, Meng Fanci, Zhou Xinyun, et al. A survey on trustworthy LLM agents: Threats and countermeasures[C]// Proc of the 31st ACM SIGKDD Conf on Knowledge Discovery and Data Mining V.2. New York: ACM, 2025: 6216−6226, articleTitle=null, refAbstract=null), Reference(id=1329419599071785017, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xiaojin, Pang Yahao, Kang Yan, et al. No free lunch theorem for privacy-preserving LLM inference[J]. Artificial Intelligence, 2025, 341: 104293, articleTitle=null, refAbstract=null), Reference(id=1329419599151476794, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=IBM BeeAI. Introduction to agent communication protocol (ACP). [EB/OL] (2024-12-03)[2026-01-03]. https://docs.beeai.dev/acp/alpha/introduction, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])], figs=[ArticleFig(id=1329419594768430073, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, label=Figure 1, caption=From computer network to AI-ModelNet, figureFileSmall=gE231+v9Vk24N0xEUilRHQ==, figureFileBig=jVI0LGd4MMgAyT88bxyVVg==, tableContent=null), ArticleFig(id=1329419594852316154, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, label=图1, caption=从计算机网络到AI-ModelNet, figureFileSmall=gE231+v9Vk24N0xEUilRHQ==, figureFileBig=jVI0LGd4MMgAyT88bxyVVg==, tableContent=null), ArticleFig(id=1329419595049448443, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, label=Figure 2, caption=Schematic diagram of AI-ModelNet, figureFileSmall=Rl5AwSVdjNIeMZ53D40GxA==, figureFileBig=2saqMifjXfUgCdhJyjZNSA==, tableContent=null), ArticleFig(id=1329419595108168700, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, label=图2, caption=AI-ModelNet的示意图, figureFileSmall=Rl5AwSVdjNIeMZ53D40GxA==, figureFileBig=2saqMifjXfUgCdhJyjZNSA==, tableContent=null), ArticleFig(id=1329419595162694653, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, label=Figure 3, caption=Hierarchical structure of AI-ModelNet, figureFileSmall=VVP92o8oBuO+BqBKxKUmVg==, figureFileBig=9Y3NTM6TmZU/S1lyHCBmUA==, tableContent=null), ArticleFig(id=1329419595225609214, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, label=图3, caption=AI-ModelNet的层次结构, figureFileSmall=VVP92o8oBuO+BqBKxKUmVg==, figureFileBig=9Y3NTM6TmZU/S1lyHCBmUA==, tableContent=null), ArticleFig(id=1329419595288523775, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, label=Figure 4, caption=Prototype system of AI-ModelNet, figureFileSmall=anem9yy59oL8gr2NH9z2RQ==, figureFileBig=dddGvFyXPb9VTEVP5Epb1Q==, tableContent=null), ArticleFig(id=1329419595364021248, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, label=图4, caption=AI-ModelNet的原型系统, figureFileSmall=anem9yy59oL8gr2NH9z2RQ==, figureFileBig=dddGvFyXPb9VTEVP5Epb1Q==, tableContent=null), ArticleFig(id=1329419595447906304, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, label=Figure 5, caption=Results comparison of singlemodel and AI-ModelNet, figureFileSmall=/34CkVfd7nS29XUoAbM98A==, figureFileBig=Q1BdjKPl0X/eBR5oMTvqXw==, tableContent=null), ArticleFig(id=1329419595506626561, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, label=图5, caption=单模型和AI-ModelNet 的结果对比, figureFileSmall=/34CkVfd7nS29XUoAbM98A==, figureFileBig=Q1BdjKPl0X/eBR5oMTvqXw==, tableContent=null), ArticleFig(id=1329419595573735426, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, label=Figure 6, caption=Stability verification of AI-ModelNet, figureFileSmall=vKvrctTn7juzmIefhaa44g==, figureFileBig=EcMrdpzFrjjN10mCz3xxbw==, tableContent=null), ArticleFig(id=1329419595640844291, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, label=图6, caption=AI-ModelNet的稳定性验证, figureFileSmall=vKvrctTn7juzmIefhaa44g==, figureFileBig=EcMrdpzFrjjN10mCz3xxbw==, tableContent=null), ArticleFig(id=1329419595703758852, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, label=Figure 7, caption=The creativity of AI-ModelNet, figureFileSmall=yt5HIs5DnVU4FzXI2d63jQ==, figureFileBig=Z42te7XD9D0ZCOl/UE9kMw==, tableContent=null), ArticleFig(id=1329419595787644933, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, label=图7, caption=AI-ModelNet 的创造性, figureFileSmall=yt5HIs5DnVU4FzXI2d63jQ==, figureFileBig=Z42te7XD9D0ZCOl/UE9kMw==, tableContent=null), ArticleFig(id=1329419595842170886, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=EN, label=Table 1, caption=

Accuracy Comparison Between a Single Model and AI-ModelNet %

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集互联前互联后
Qwen 2.5路由式DuetNet
SimpleMath729692
C-Eval707078
BoolQ828484
MMLU868688
), ArticleFig(id=1329419595909279751, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, language=CN, label=表1, caption=

单一模型与AI-ModelNet的准确率对比

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集互联前互联后
Qwen 2.5路由式DuetNet
SimpleMath729692
C-Eval707078
BoolQ828484
MMLU868688
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202550223, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550223, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202550223, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202550223, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1777564800000, fullTextJson=null, articleText=null, reference=null)
收藏切换
模型互联网:概念、现状和未来
李哲涛 , 曾曦玉 , 王建辉 , 肖勇 , 刘忠仁 , 吴俊儒 , 赖俊杰 , 黄纪俊 , 龙赛琴
计算机研究与发展 | 网络技术 2026,63(5): 1305-1318
收起
收藏切换
计算机研究与发展 |网络技术 2026 , 63 (5) : 1305 -1318
模型互联网:概念、现状和未来
全屏
[Author(id=1329419591987606467, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liztchina@hotmail.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592088269765, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419591987606467, language=EN, stringName=Zhetao Li, firstName=Zhetao, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1980. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent network and artificial intelligence

"}, bioImg=null, bioContent=

born in 1980. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent network and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592193127366, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419591987606467, language=CN, stringName=李哲涛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"NGdjkywb3qvUT3z4kAWR1Q==","content":"

1980年生。博士,教授,博士生导师。CCF会员。主要研究方向为智能网络、人工智能

"}, bioImg=NGdjkywb3qvUT3z4kAWR1Q==, bioContent=

1980年生。博士,教授,博士生导师。CCF会员。主要研究方向为智能网络、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419592272819144, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592344122314, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592272819144, language=EN, stringName=Xiyu Zeng, firstName=Xiyu, middleName=null, lastName=Zeng, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1999. PhD candidate. Her main research interests include data privacy and artificial intelligence

"}, bioImg=null, bioContent=

born in 1999. PhD candidate. Her main research interests include data privacy and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592407036875, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592272819144, language=CN, stringName=曾曦玉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"ThuA7iI4JM5xMkW0AtHHBQ==","content":"

1999年生。博士研究生。主要研究方向为数据隐私、人工智能

"}, bioImg=ThuA7iI4JM5xMkW0AtHHBQ==, bioContent=

1999年生。博士研究生。主要研究方向为数据隐私、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419592465757133, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592545448911, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592465757133, language=EN, stringName=Jianhui Wang, firstName=Jianhui, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1997. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

"}, bioImg=null, bioContent=

born in 1997. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592616752080, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592465757133, language=CN, stringName=王建辉, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"T6lRGdIWl0ynNHygDmhhzw==","content":"

1997年生。博士研究生。主要研究方向为移动边缘计算、人工智能

"}, bioImg=T6lRGdIWl0ynNHygDmhhzw==, bioContent=

1997年生。博士研究生。主要研究方向为移动边缘计算、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419592683860946, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592738386900, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592683860946, language=EN, stringName=Yong Xiao, firstName=Yong, middleName=null, lastName=Xiao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

"}, bioImg=null, bioContent=

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592797107157, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592683860946, language=CN, stringName=肖勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"XESCVxqMbkWchxx2waZuxQ==","content":"

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

"}, bioImg=XESCVxqMbkWchxx2waZuxQ==, bioContent=

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419592851633111, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419592927130585, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592851633111, language=EN, stringName=Zhongren Liu, firstName=Zhongren, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1996. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

"}, bioImg=null, bioContent=

born in 1996. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419592985850842, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419592851633111, language=CN, stringName=刘忠仁, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"j3yRPyRoQ6sUj5BXLMRmlw==","content":"

1996年生。博士研究生。主要研究方向为移动边缘计算、人工智能

"}, bioImg=j3yRPyRoQ6sUj5BXLMRmlw==, bioContent=

1996年生。博士研究生。主要研究方向为移动边缘计算、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419593069736924, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419593145234398, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593069736924, language=EN, stringName=Junru Wu, firstName=Junru, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

"}, bioImg=null, bioContent=

born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419593220731871, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593069736924, language=CN, stringName=吴俊儒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"Sybl90+Fgjtf1ETSqKgGWA==","content":"

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

"}, bioImg=Sybl90+Fgjtf1ETSqKgGWA==, bioContent=

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419593279452129, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419593359143907, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593279452129, language=EN, stringName=Junjie Lai, firstName=Junjie, middleName=null, lastName=Lai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 2001. Master candidate. His main research interests include large language models and natural language processing

"}, bioImg=null, bioContent=

born in 2001. Master candidate. His main research interests include large language models and natural language processing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419593464001508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593279452129, language=CN, stringName=赖俊杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"3+jwjjn5LpZy/4GU9oaVVw==","content":"

2001年生。硕士研究生。主要研究方向为大模型、自然语言处理

"}, bioImg=3+jwjjn5LpZy/4GU9oaVVw==, bioContent=

2001年生。硕士研究生。主要研究方向为大模型、自然语言处理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419593543693286, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=7, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419593623385064, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593543693286, language=EN, stringName=Jijun Huang, firstName=Jijun, middleName=null, lastName=Huang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 2000. Master candidate. His main research interests include large language models and cybersecurity

"}, bioImg=null, bioContent=

born in 2000. Master candidate. His main research interests include large language models and cybersecurity

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419593715659753, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593543693286, language=CN, stringName=黄纪俊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"dtEKWFPoTbbTFxFAjiPSig==","content":"

2000年生。硕士研究生。主要研究方向为大模型、网络安全

"}, bioImg=dtEKWFPoTbbTFxFAjiPSig==, bioContent=

2000年生。硕士研究生。主要研究方向为大模型、网络安全

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])]), Author(id=1329419593778574315, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, orderNo=8, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1329419593858266093, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593778574315, language=EN, stringName=Saiqin Long, firstName=Saiqin, middleName=null, lastName=Long, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Science and Technology, Jinan University, Guangzhou 510632, bio={"content":"

born in 1986. PhD, professor, PhD supervisor. Member of CCF. Her main research interest includes edge computing

"}, bioImg=null, bioContent=

born in 1986. PhD, professor, PhD supervisor. Member of CCF. Her main research interest includes edge computing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1329419593929569262, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, authorId=1329419593778574315, language=CN, stringName=龙赛琴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=暨南大学信息科学技术学院 广州 510632, bio={"img":"YZJpbak8BByViLYiEywJKQ==","content":"

1986年生。博士,教授,博士生导师。CCF会员。主要研究方向为边缘计算

"}, bioImg=YZJpbak8BByViLYiEywJKQ==, bioContent=

1986年生。博士,教授,博士生导师。CCF会员。主要研究方向为边缘计算

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1329419591878554559, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, xref=null, ext=[AuthorCompanyExt(id=1329419591886943168, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Science and Technology, Jinan University, Guangzhou 510632), AuthorCompanyExt(id=1329419591895331777, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1329419588833489818, companyId=1329419591878554559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=暨南大学信息科学技术学院 广州 510632)])])]
李哲涛 , 曾曦玉, 王建辉, 肖勇, 刘忠仁, 吴俊儒, 赖俊杰, 黄纪俊, 龙赛琴
作者信息
  • 暨南大学信息科学技术学院 广州 510632
作者简介:

1980年生。博士,教授,博士生导师。CCF会员。主要研究方向为智能网络、人工智能

1999年生。博士研究生。主要研究方向为数据隐私、人工智能

1997年生。博士研究生。主要研究方向为移动边缘计算、人工智能

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

1996年生。博士研究生。主要研究方向为移动边缘计算、人工智能

2000年生。博士研究生。主要研究方向为移动边缘计算、人工智能

2001年生。硕士研究生。主要研究方向为大模型、自然语言处理

2000年生。硕士研究生。主要研究方向为大模型、网络安全

1986年生。博士,教授,博士生导师。CCF会员。主要研究方向为边缘计算

AI-Model Network: Concept, Current State and Future
Zhetao Li , Xiyu Zeng, Jianhui Wang, Yong Xiao, Zhongren Liu, Junru Wu, Junjie Lai, Jijun Huang, Saiqin Long
Affiliations
  • College of Information Science and Technology, Jinan University, Guangzhou 510632
  • born in 1980. PhD, professor, PhD supervisor. Member of CCF. His main research interests include intelligent network and artificial intelligence

    born in 1999. PhD candidate. Her main research interests include data privacy and artificial intelligence

    born in 1997. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

    born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

    born in 1996. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

    born in 2000. PhD candidate. His main research interests include mobile edge computing and artificial intelligence

    born in 2001. Master candidate. His main research interests include large language models and natural language processing

    born in 2000. Master candidate. His main research interests include large language models and cybersecurity

    born in 1986. PhD, professor, PhD supervisor. Member of CCF. Her main research interest includes edge computing

出版时间: 2026-05-01 doi: 10.7544/issn1000-1239.202550223
文章导航
收藏切换

计算机的主要功能在于计算与处理,互联网的价值在于共享与协作。计算机催生互联网,互联网放大计算机的价值。互联网、云计算与大数据的快速发展推动了人工智能迈入大模型时代。然而,大模型在实际应用中面临训练成本高昂、泛在部署困难等挑战,促使大模型朝轻量化、私有化及垂直化方向发展。随着异构模型的急速增长和广泛分布,模型间的交互协同成为大模型发展亟须突破的瓶颈问题。受计算机互联网的发展模式启发,提出模型互联网(AI-ModelNet)的概念、构想及系统架构,它是一种通过构建模型间通路,实现互联互通、能力共享与协同推理等的新范式。首先,简要介绍了单一模型与多模型场景的发展现状;然后,系统性地阐述了模型互联网的总体构想与层次结构,并结合原型系统与相关应用实例验证了其可行性与实用性;最后,初步展望了未来研究的主要方向。

大模型  /  多模型协作  /  模型交互  /  模型互联网  /  互联网

While the primary function of computers lies in computation and processing, the core value of the Internet is rooted in sharing and collaboration. Computers create the Internet, and the Internet empowers the value of computers. The rapid development of the Internet, cloud computing, and big data is pushing artificial intelligence into the era of large models (LMs). However, the practical application of LMs is currently hindered by high training costs and deployment complexities, driving a shift toward lightweight, private, and domain-specific models. With the rapid proliferation and wide distribution of heterogeneous models, enabling effective interaction and collaboration among them has emerged as a critical bottleneck that urgently needs to be addressed in LM development. Drawing inspiration from the development of the Internet, we propose the concept, vision, and system architecture of world wide AI-model network (AI-ModelNet). It is a novel paradigm that achieves interconnection, capability sharing, and collaborative reasoning by establishing pathways between models. We first briefly review the current state of single-model and multi-model research. Subsequently, the systemic vision and hierarchical architecture of AI-ModelNet are articulated, followed by validation of the framework’s feasibility through a prototype system and diverse application cases. Finally, key directions for future research are discussed preliminarily.

large models  /  multi-model collaboration  /  model interaction  /  AI- model network  /  the Internet
李哲涛, 曾曦玉, 王建辉, 肖勇, 刘忠仁, 吴俊儒, 赖俊杰, 黄纪俊, 龙赛琴. 模型互联网:概念、现状和未来. 计算机研究与发展, 2026 , 63 (5) : 1305 -1318 . DOI: 10.7544/issn1000-1239.202550223
Zhetao Li, Xiyu Zeng, Jianhui Wang, Yong Xiao, Zhongren Liu, Junru Wu, Junjie Lai, Jijun Huang, Saiqin Long. AI-Model Network: Concept, Current State and Future[J]. Journal of Computer Research and Development, 2026 , 63 (5) : 1305 -1318 . DOI: 10.7544/issn1000-1239.202550223
计算机的主要功能在于计算与处理,互联网的价值在于共享与协作。在计算机的发展历程中,随着技术的进步与广泛普及,其研究重心逐步由单机算力增强转向网络通信机制。在1974年,TCP/IP协议的问世为网络报文传输提供了标准,奠定了现代互联网的基础。1989年,HTTP协议的提出推动了万维网[1]的兴起,彻底改变了人类社会的信息交流方式,数字空间、信息空间和网络空间等成为人类社会信息交流的重要媒介。因此,计算机催生互联网,互联网则持续拓展计算的应用边界。计算机和互联网相辅相成,互联放大了计算价值。
在人工智能(artificial intelligence,AI)的发展中也同样经历了从简单任务到复杂任务的发展路径。人工智能模型的发展大致经历了3个阶段:神经网络阶段、深度学习阶段以及大规模预训练模型阶段。在神经网络阶段,模型结构相对简单,主要用于解决基本的分类和回归问题,为深度学习奠定了根基;在深度学习阶段,网络结构逐步加深,模型能够处理更复杂的数据特征和任务需求,并被广泛应用于图像识别、语音识别和自然语言处理(NLP)等领域;Transformer架构[2]的提出标志着人工智能步入了大规模预训练模型阶段,在显著提升并行计算效率的同时实现性能突破。如图1所示,计算机的发展实现了从简单计算到复杂计算,而互联网实现了从孤立计算到全球互联的范式跃迁。受互联网发展的启发,模型互联有望实现模型价值在系统层面的放大。
当前的人工智能处于参数爆炸时代。然而,现有人工智能模型面临训练硬件成本、数据成本和人力成本高昂,部署存储资源消耗大且参数规模红利微弱的困境[3]。因此,轻量化、私有化与垂直化部署成为主流趋势。当前模型之间割裂缺少互联,“模型孤岛”现象逐渐显现。在实际应用中,单一模型面临多重挑战。比如模型往往会无意识地继承训练数据的偏见[4],从而影响其决策的客观性;在知识盲区或不确定场景下,模型可能因自身偏好和幻觉输出不实信息[5]。通用模型在领域数据上进行针对性训练后,通用能力往往会有所下降[6]。正如计算机互联实现资源共享与协同处理以提升整体系统价值,模型互联互通也有望成为迈向通用人工智能(artificial general intelligence,AGI)的重要路径。
在复杂系统中,高阶能力的形成往往并非源于单一主体能力的无限增强,而是多个有限个体在相互联系与协同作用中涌现的结果[5-9]。这一规律在自然系统、社会系统以及工程系统中均具有普遍性:个体能力存在不可逾越的边界,而个体之间的联系则为信息互补、认知纠偏与能力放大提供了结构性条件。从这一视角上看,系统的智能水平更多取决于其组织方式与交互机制,而非单个组件的最优性能。该系统性规律在经验层面早已被广泛认知,常被概括为“三个臭皮匠,顶个诸葛亮”,即集体智慧在适当的组织与协作条件下,往往能够超越个体的能力上限。其本质在于多个体交互带来的协同增益。不同个体在知识背景、推理路径与决策偏好上的差异,使系统能够在交互过程中不断修正局部偏差,弥补认知盲区,并在整体层面形成更具鲁棒性的判断结果[10]。模型协作的价值并不是抹平每个“盲人”个体的感知局限,而是多元互证中构建坚实共识,通过动态整合局部感知不断趋近“大象”整体真相。因此,个体之间的联系并非附属关系,而是高阶能力产生的必要条件。
将这一系统性视角引入人工智能领域,可以发现模型之间的互联并非偶然选择,而是一种内在必然。单一模型无论在规模或性能上如何提升,其内部表征仍受限于结构容量与数据质量,而模型之间的联系则为跨模型知识互补与推理协同提供了可能性。通过构建模型之间的稳定联系,使多个模型在协作中形成群体智能,能够在系统层面突破单一模型能力的固有边界。这也是“普遍联系”“量变质变”哲学原理的具体体现,即多模型随着协作深度的增加,最终有望推动智能系统在认知层次、任务泛化与自主协同等方面实现“质”的跃迁。统计显示,目前全球已有超过1300个人工智能大模型,涵盖主要知识领域[11]。 如何有效组织与协调现有模型,以互联推动模型网络化,已成为提升智能系统整体效率的重要方向。
如图1所示,若将模型视为计算机中封装的智能资源,则模型间的交互过程可类比为网络节点间的信息传输。因此,本文提出“模型互联网(AI-ModelNet)概念”。模型互联网是一种通过构建标准化模型间信息通路,实现模型的动态发现、按需组合与协同推理等的新范式。模型互联网强调模型节点之间的互联互通与网络级协作,将模型抽象为可持续发现与组合的能力节点,以支撑开放、异构且可演化的智能系统模型互联互通实现了人工智能与大算力、大数据的解耦,有效降低智能技术对算力与数据资源的强依赖性。因此,模型互联网有望成为未来人工智能发展的催化剂。
本节依次探讨现有单一模型以及多模型协作领域的研究进展。通过系统性的分析阐明模型互联网与现有研究路径的根本差异。
随着大规模预训练技术的快速发展,单一大模型在自然语言处理(NLP)、信息检索等任务中展现出显著优势。伴随Transformer架构的演化,众多性能的生成式大模型相继涌现,形成“百模竞发”的发展格局。代表性模型如GPT系列[12]、LLaMA系列[13]、DeepSeek系列[14]、Qwen系列[15]与Kimi系列[16]模型,其应用拓展至语言生成、知识问答、推理与工具调用等多种场景,并在自动驾驶[17]、智能助手[18]、文学创作[19]等领域得到探索与实践。
单一大模型在实际应用中仍面临诸多挑战。首先,模型的知识与价值边界受训练数据影响。其次,模型可能存在“幻觉”现象,即逻辑连贯但事实错误的信息输出[20]。此外,大模型推理依赖巨大算力、存储与能耗资源[21],限制了其在资源受限场景中的部署。最后,特定任务的专有训练与微调的模型,往往会以削弱其通用性能为代价。
面对多样化任务需求、复杂环境适配与系统长期演进等挑战时,单一大模型架构在泛化性、高效性与灵活性等方面的瓶颈日益凸显。这促使研究者开始探索具备协同能力的多模型架构,通过任务分解、模型互补与灵活路由等机制,实现能力模块化、推理透明化与模型更新自由化,从而为人工智能研究提供新的发展方向。
近年来,多模型协作逐渐成为构建灵活、高效智能系统的重要路径。多模型协作的核心思想旨在通过模型间能力互补、任务分解与结构化路由,实现复杂任务的分治推理,并增强系统稳健性。现有研究主要集中于3类策略[22]:模型融合、输出集成与动态路由。
模型融合通过整合多个预训练模型的参数以构建统一模型,追求结构上的协同与性能压缩。Ties-Merging方法[23]则引入轻量策略以缓解参数符号冲突和幅度失衡问题。Twin-Merging方法通过将专家模型的知识分解为共享知识与独占知识,然后根据输入动态融合两类知识,有效解决了知识干扰和测试数据异构导致的性能下降问题[24]。
输出集成聚焦于在保留模型独立性的前提下,通过输出融合实现更稳健的推理。DeePEn方法[25]提出双向词汇映射机制以打通异构模型的语义表示空间。王建辉等人[26]提出一种token级并联协作方法,通过通信机制连接多个模型节点,实现跨设备的高效交互推理。吴俊儒等人[27]设计的互评串联协作机制实现模型间自治答案优化。此外,多源知识融合框架[28]也展现出多模型协作在任务分工与知识整合方面的优势。Wu等人[29]构建了面向协作的多模型系统,通过角色分配实现智能体间的能力互补,从而提升系统整体性能。
动态路由机制通过在推理过程中动态选择最合适的模型执行子任务,实现性能与成本的平衡,进一步增强了多模型系统的灵活性。Ong等人[30]提出的RouteLLM基于人类偏好数据引导路由器学习模型选择决策。BEST-Route方法[31]结合模型与采样策略进行双重选择。GraphRouter方法[32]采用图结构建模模型与查询间的语义关联。RCR-Router方法[33]引入角色感知记忆机制实现上下文信息的精准传递。TO-Router方法[34]则在工业场景部署中验证了基于查询特征与专家能力映射的高效选择机制。
尽管上述方法在多模型架构设计方面取得了积极进展,但当前研究仍面临三大挑战:一是协作任务设计缺乏通用性,仍依赖特定场景配置;二是模型间交互机制固化,难以适配动态多任务的实际环境;三是系统高度依赖集中算力资源,导致部署成本高和扩展性不足。虽然现有多模型协作研究已奠定了良好基础,但其在开放、异构与分布式环境中的适用性仍有待提升。这也进一步凸显了“模型间互联”作为通用基础设施的重要价值,即:通过建立松耦合、可通信及可协作的全球模型互联网络体系,突破当前协作范式的边界,推动智能系统向高灵活性、高扩展性与长期自治方向演进。
综上所述,多模型协作系统与模型互联网均以实现模型间的协作与能力互补为目标,但二者在范式预设上存在本质差异。前者多依赖静态架构与预定义规则,其能力上限受制于底层大模型与集中式控制机制;而模型互联网则致力于构建一个开放式、标准化及分布式的模型互联架构,其中模型被抽象为可被动态发现、按需组合与灵活调用的标准化能力节点,以适应复杂多变的任务环境。模型互联网的目标不仅在于任务层面的协同执行,更在于促进模型能力与知识的跨域流动与全局共享。因此,现有的多模型协作系统可被视为一种实现模型互联网的早期实践与前期探索。它为模型如何交互、协同与自治提供了重要技术思路,是连接当前实践与未来模型互联网生态的重要桥梁。
本节提出了模型互联网的构想及其层次结构,并展示了模型互联网的应用实例。
模型互联网是一种通过构建模型间标准化通路,实现模型互联互通、能力共享与协同推理的新范式。模型互联网依托现有互联网基础设施运行,但其连接对象和组织目标与互联网不同:互联网以计算节点与数据资源为核心,通过通用通信协议实现信息传输;而模型互联网以人工智能模型为节点单元,基于协作规则在异构模型之间构建信息通路。因此,互联网为模型互联提供通信基础支撑。现有微小模型、巨大模型、低配模型、免费模型、通用模型、领域模型和私有模型等丰富异构模型为模型互联网提供了基础条件。模型互联网具有优化输出结果、消除个体偏见等特点;提供稳定服务、模型分布式更新等优点;智能涌现、智能与算力/数据解耦等潜能。因此,是模型的发展催生模型互联网,模型互联网也将放大模型的价值。
模型互联网的示意图如图2所示。模型互联网是由若干边端设备以及服务器上私有化部署的模型组成。它可应用HTTP,MCP等协议,使得模型之间进行交互形成通信链路,由此构建出动态的模型交互网络。模型互联网允许自由地接入或退出模型,实现推理的“即插即用”。它根据任务性质与实时状态,遴选出能力匹配的模型,进而依据预设的协作策略进行调度与执行,从而在逻辑上动态形成一条最优的模型链路。互联网连接的是计算节点;模型互联网连接的是模型,分享的是知识。模型互联网具有以下特征:
1)互通性
借鉴了互联网的分布式网络结构,模型互联网引入了分布式与自由组网的设计理念,强调模型间的自治通信。因此,逻辑上模型互联网中的模型是互联互通的。在该体系中,模型作为网络节点通过统一的模型互联通信协议实现消息传递与共享。模型依据任务需求动态发现其他节点,从而形成灵活可扩展的模型协作网络。系统支持节点的自组织与拓扑重构,当模型上线、离线或性能变化时,协作网络可自动调整结构以保持系统稳定与运行高效。
此外,分布式的自由组网机制赋予了模型互联网更高的鲁棒性与弹性。在此架构下,模型节点之间不存在固定的主从关系,任何节点在必要时承担任务协调、结果融合或知识共享的角色。这种动态多对多、弱耦合的协作模式打破了传统模型系统的层级约束,为实现跨域、跨平台的多模型协同奠定了基础。
2)多样性
模型互联网通过组织具备差异化能力的模型节点,实现跨领域任务的协同处理,而不再依赖单一模型的知识边界。不同模型可依据其专长承担特定子任务,从而在系统层面提升整体效率与结果质量。这种多样化的模型协作使系统在面对复杂与不确定任务时,具备更强的适应性和灵活性。
不同于传统多模型系统仅支持高层agent级协作,模型互联网支持从宏观任务级到微观span级或token级的跨粒度协作,能够满足不同应用场景对协作灵活性和精细度的要求。这种多模型的协作不仅扩展了任务处理方式,还促进了不同领域知识的联动与共享,从而能够应对更复杂和更多样化的应用场景。
3)动态性
模型互联网构建了一个开放、协同及动态演化的智能生态系统。模型节点可随时接入或退出网络,支持分布式更新与能力演进,从而适应模型快速迭代的现实需求。
与此同时,下游任务对模型能力的需求呈现出动态变化的能力谱系。模型之间的交互链路不再是预先定义的,而是随着任务流实时生成与调整。由此,模型互联网的整体拓扑结构表现为一个持续重构的动态图网络,而非固定不变的协作架构。
综上所述,模型互联网通过分布式部署与自由组网机制,使模型节点能够自主建立连接并协同完成复杂任务。该体系在增强系统稳定性、鲁棒性与扩展能力的同时,显著降低了模型更新与调度的工程复杂度。模型节点可直接访问其他节点提供的能力服务,无需重复部署全部模型,从而实现模型能力的动态发现、调用与任务分配。通过支持多类型、多粒度的协作模式,模型互联网为构建灵活、高效且可持续演化的模型生态系统提供了系统性支撑。
模型互联网以云边端物理设备与互联网通信协议为基础。各类模型根据其规模与资源需求分别部署于云端、边缘设备及端侧设备中,模型间的协同与交互则体现为基于HTTP协议的信息交换与服务调用。如图3所示,模型互联网由资源层、服务层、交互层以及应用层组成。
1)资源层
资源层作为模型互联网系统的核心基础设施,负责对各类基础资源进行统一管理。其为交互层提供了必要的支持,确保系统高效且可持续的运行。此外,资源层需要具备高度灵活性,以适配各类模型自由接入和退出系统的需求。在模型更新或处理复杂任务时,系统应能够迅速调整资源配置。同时,通过有效的资源管理机制,资源层可以有效降低运营成本,提升用户体验。
在模型互联网中,资源层不再局限于传统云计算应用中的服务器与网络设备,而是拓展为涵盖硬件资源、软件资源与模型资源的综合性资源集合。其中,硬件资源则覆盖云端高性能GPU/TPU集群,边缘侧AI加速节点以及终端设备等异构计算资源。软件资源则构建于容器化与微服务架构之上,整合了大模型推理引擎、服务运行环境等中间件,为模型服务提供标准化、可移植、高可用的运行时环境。模型资源包括云端通用大模型以及各种边端部署的模型,用于实现模型能力的分层供给与按需调用,该资源通过模型池进行管理。资源层以开放式接口为基石,支持第三方模型提供方、算力运营商与应用开发者自由接入与共享资源,逐步构建起模型互联网的新型协作基础设施。
2)服务层
服务层是模型互联网中实现智能任务执行的核心枢纽,承担着任务编排与资源调度的双重职责。其核心功能主要包括将复杂任务分解为独立的子任务、动态更新系统资源状态、智能动态调度以及模型负载的均衡分配。具体工作流程如下:
首先,服务层的智能模块需要对交互层所提交任务进行语义分析。通过服务层内置的任务分析模块对任务意图、数据特征等进行多层次拆解,将复杂请求自动分解为一组原子化、可调度化的子任务,并为每个子任务打上多维问题标签。同时,服务层持续从资源层获取海量节点的实时运行状态,包括各边缘设备与云服务的算力余量、网络延迟等,并结合全局模型数据中心中存储的模型版本、推理延迟等信息,构建出一张动态、细粒度的资源能力图谱。然后,通过多维度标签匹配机制,系统将每个子任务的需求与资源节点的能力标签进行智能匹配,形成候选资源集合,并进行联合优化匹配。最后,监控执行过程中的延迟波动与异常状态,在节点失效或性能劣化时自动触发热切换与重调度机制,保障服务可靠性。
3)交互层
交互层作为系统决策与控制的核心环节,需要根据服务层输出的匹配结果,动态构建面向任务特性的通信网络拓扑结构。在此基础上,交互层依据协作策略与路由策略做出动态调整,实现跨节点的高效协同推理与数据交互。具体工作流程如下所示:
交互层首先根据服务层输出的模型-任务匹配结果,针对用户发起任务请求动态构建自适应的协作通路。随后,交互层应用协作策略与路由策略,实现跨异构节点的高效协同。其中,协作策略用于定义各参与节点在任务执行过程中的协作流程,确保模型计算或推理任务在算力异构的节点环境中实现高效协同。例如,通过引入模型串行与并行协作推理算法,可对多模型输出进行加权融合、投票决策和辩论等,实现各类模型推理结果的统一共识。路由策略基于实时网络拓扑状态与通信负载动态规划消息传输路径,综合考虑最短延迟、链路稳定性、模型适配性等多维指标进行路由选择。路由策略以提升数据传输效率与整体响应性能为目标,尽可能减少跨节点通信延迟与带宽开销,系统可采用HTTP协议作为跨节点通信的基线传输机制。此外,为确保兼容性与可扩展性,通过轻量级消息封装与状态同步机制以支撑高并发、低延迟的模型协作需求。
4)应用层
应用层是互联网模型的阶值实现层,负责将跨类型、跨平台、多模态智能模型的深度融合与高效协同,封装为一个可适配各类任务场景的统一接口。其核心价值在于打破“模型孤岛”导致的单一化应用的壁垒,满足现实世界中高度复杂、动态演化以及多源异构的系统性需求,如科学探索、智能制造等典型场景。
在科学探索中,模型互联网能通过整合物理建模、数据驱动与知识推理等不同类型的模型,实现对复杂科学问题的联合求解。无论是气候变化预测,还是新药研发,系统均能自动调度与协调各环节模型,完成传统方式难以企及的高维认知任务。在产业制造中,模型互联网系统能支撑智能制造、产品研发等场景下的全链路智能决策,将缺陷检测、供应链优化、能耗调控等分散环节整合为动态响应的整体,实现产业智能化升级。
应用场景的持续拓展,将驱动模型互联网向各领域深度渗透,逐步演进为通用模型与专有模型协同增强的模型网络。日益丰富的应用需求推动模型协同机制的进化,而更强大的协同能力又进一步拓展新的应用边界。这一动态演进机制,使其有望成长为支撑前沿科学研究突破、产业智能化升级的核心基础设施。
本节详细描述了一个模型互联网系统搭建的实例,并通过在该系统上的实验展现了其良好性能。
图4展示了一个模型互联网原型系统。该系统基于llama.cpp和分布式集群管理等技术,实现了对集群内设备和模型的管理,以及对集群内异构设备与模型资源的整合与高效调度。作为模型互联网概念的工程化验证载体,该原型系统为后续模型协作机制的研究提供了实验平台与验证基础。下面将围绕模型互联实现、模型管理及接入控制机制,介绍该系统的设计与实现。
该系统集成了Jetson嵌入式模块、树莓派与GPU工作站等多种异构设备作为模型部署节点,以模拟真实场景中多样化计算资源。该系统根据各节点的实际算力,为其部署相应参数规模的模型,从而有效模拟了真实模型互联网中模型能力的异构性。
此外,为便于跨节点统一管理推理框架与模型权重,该平台基于Kubernetes构建了一套完整的调度方案,涵盖模型的部署、模型池的构建与分发、推理任务调度。通过将llama.cpp框架封装为标准化的Docker镜像,并实现模型权重与推理框架的分离,系统在资源利用与模型管理之间实现了解耦,从而在架构层面保障了模型互联网系统的整体可扩展性。
在模型互联网的原型系统中,用户首先在界面上选择想要使用的推理模型和协作范式,并将请求信息提交到调度后端,当后端接收到请求后触发调度流程。接着,调度器查询数据库,获取相关模型节点信息与调度信息,向调度端发起调度请求,并记录该请求日志。最后,调度端解析响应后,更新用户请求状态,将推理结果写入数据库,并向前端返回结果,完成服务闭环请求。
在调度执行阶段,系统首先在集群与数据库中检索目标模型的部署状态。若模型已部署于可用节点,则根据该节点的实时资源占用情况决定是否接受请求;若无节点部署该模型,调度器将选择一个合适的空闲节点执行动态部署。随后,当目标节点启动时,其预置的初始化程序从调度请求中提取待部署模型信息,并优先检查本地缓存是否已存在对应权重。若未缓存,程序将从系统内置的模型权重库中拉取模型权重及启动参数,加载模型并完成部署,为后续推理做好准备。
为探究模型互联网的精准度、稳定性、创造性以及泛在性等,本文选取独立部署在AI-ModelNet系统中的模型作为研究对象,具体包括:树莓派8 B上的Qwen1.5-7B、Jetson 16 GB上的Glm-4-9B、Jetson 64 GB上的Meta-Llama-3.1-8B、4090工作站48 GB上的Mistral-Neom-Instruct-2407。为确保实验的一致性,本文设置 Top-K=3生成回答。
AI-ModelNet系统为所有接入模型提供标准化接口,实现了模型间的无缝信息交换。在路由式协作方面,根据模型的能力向量和任务属性选取最优输出作为最终回答。在贪心token级并联方式方面,多模型并行输出token候选集,根据贪心策略选取候选集中概率最大的token。另外,系统集成了DuetNet[23]推理架构,其通过联合截断策略筛选来自各模型的token候选集,进而融合生成优化结果。
1)模型互联网的精准度分析
如图5所示,本文选取光合作用相关的客观问题,在固定提示词(仅要求输出答案)的条件下,对比了模型独立作答与经AI-ModelNet贪心token级策略优化后的结果,以评估问答性能的提升。该问题的正确结果为C,根据实验结果可知单一模型在答案准确性和简洁性上存在不足。部署在小设备上的Qwen在分析过程中产生错误结论,影响了回答的可靠性。然后,Glm和Mistral-Nemo虽然能够提供详细分析,但在回答中包含多余信息,偏离问题的核心需求。显然AI-ModelNet在贪心token级并联策略上的输出结果在准确性和简洁性上明显提升,能够满足问题对标准答案的要求。从该示例可以发现模型互联能够整合各模型的优点,并通过交叉验证和优化选择模型贡献的部分,减少了单一模型可能带来的差错和冗余。
2)模型互联网的稳定性分析
模型互联网面对模型更替或网络中断等情况,其协同机制依然能够保障服务的稳定性和连续性。在验证性实验中,本文选取了Yi-6B,Internlm2-7B,Llama3-8B,Mistral-7B,Qwen-14B等模型,统一设置在线率为1,0.9,0.8,0.7,0.6,0.5,测试集选择MMLU数据集。通过对比单一模型与AI-ModelNet在贪心token级并联策略的回答准确性,评估互联协作机制在不同在线率下对回答质量和系统稳定性的影响。图6表明单一模型的在线率与回答质量呈现明显的正比关系,即当在线率逐步提升时,提供高质量服务的概率也增大。这一现象的主要原因是单一模型无法正常提供服务,影响了回答质量的稳定性和准确性。然而,在模型互联网中,在线率对回答质量几乎没有影响。即使部分模型断开连接或因网络故障无法提供服务,协作机制仍然能够通过其他可用模型进行任务分配和补充,从而提供持续稳定的服务。此外,实验结果进一步表明,模型协作不仅有效提升了系统的容错能力和鲁棒性,还在整体回答质量方面展现出显著的优势。这充分证明了模型互联网在低在线率和复杂场景时的可靠性和优越性。
3)模型互联网的创造性分析
通过前文分析可知,单一模型由于训练数据集的差异,在不同领域的知识表现上存在局限性,难以在某些领域提供高质量的回答。此外,LMs本身具有过度自信的倾向——即使缺乏相关知识,也倾向于生成看似合理但实际不准确的内容,从而损害输出的真实性和可靠性。为验证模型互联所激发的创造性,本文通过对同系列模型Qwen1.5-7B,Qwen2.5-7B在AI- ModelNet贪心token级并联策略下的协作结果分析模型互联所带来的创造潜力。选择同系列模型旨在控制架构范式与训练数据分布这一核心变量,以探究交互能否催生非预期创新。
实验结果如图7所示,在该示例中,正确答案为C。尽管2个模型单独运行时均给出了错误答案,但当它们通过协作互联后,却成功输出了正确结果。这不仅表明模型互联能够提升回答的正确性,也进一步增强了系统的创造性。各模型通过发挥自身独特的知识优势,在协作中相互配合、共同完成推理,不仅优化了整体性能,还促进了知识的深度融合与创新。结果进一步表明,在处理复杂或跨领域问题时,模型协作机制能够有效利用不同模型之间的互补性,探索更加丰富多样的解题路径与创新方案,从而生成更具启发性和创造力的内容。这种多模型协同不仅提高了系统对复杂任务的适应能力,还推动了输出内容在多样化与创新性方面的提升,拓展了人工智能模型在知识创造与解决实际问题中的应用潜力。
4)模型互联网的泛化性分析
为进一步探索模型互联网的泛化潜力,本研究基于单一模型(Qwen2.5-7B-Instruct)开展了实验,比较其在接入AI-ModelNet前后的推理性能变化,具体数据如表1所示。在模型接入模型互联网后,本文分别考察了2种协作机制:token级协作的 DuetNet 和典型的路由式协作策略,以系统评估不同协作方式对模型性能的影响。
实验采用的数据集如下:
SimpleMath[35]用于训练和评估模型基础数学应用题能力的数据集。
C-Eval[36]用于评测大模型的知识和逻辑推理能力,涉及52个学科的多选题。
BoolQ[37]段落级英文判断题,包含12000条数据,用于探究模型的多句推理能力。
MMLU[38]用于全面评估模型的通用知识和问题的解决能力,涵盖了57个学科以及不同专业程度的多选数据集。
由表1结果可见,模型互联后的整体准确率优于单一模型。当模型采用路由式协作策略时,与单一模型相比,该方式在SimpleMath任务上的准确率提升了24个百分点,这主要得益于其能够优先调用模型互联网中与该任务最契合的模型。其次,DuetNet协作策略在互联后表现出广泛的任务适应性。相较于未互联的单一模型,该策略在SimpleMath,C-Eval,MMLU数据集上的准确率分别提升了20个百分点、8个百分点、2个百分点。该提升源于模型间通过汇聚推理共识降低推理过程的错误累积,从而提高推理准确率。上述结果表明,接入模型互联网能够突破单一模型的能力边界,有效弥补其在任务覆盖与泛化性能方面的局限。一方面,互联协作机制可显著增强模型在多样化任务上的表现;另一方面,协作策略的实施有助于降低用户对模型输出性能的不确定性,从而提升系统可靠性与用户满意度。
以上对模型互联后的准确性、稳定性、创造性以及泛化性的实验结果表明:模型间的协作可以推动模型知识的互补与增强,并且在提高复杂问题解答的整体质量上具有显著优势。这种互联协作模式通过集成多个模型的能力,实现动态资源调度与智能任务分配,从而在多样化场景下提供更稳定的模型服务支持。同时,多模型协作还能有效规避单点故障带来的风险,通过模型之间的互补与协同优化,提高系统整体的鲁棒性、响应速度以及服务质量,从而确保系统在复杂多变的需求环境中依然能够高效运行,满足用户的长期稳定需求。此外,模型互联网还具备良好的可扩展性,可以随着技术的发展和新模型的引入进行迭代升级,进一步强化协作能力,为各类应用场景提供持续可靠的解决方案。
1)模型异构性的分析
模型互联网中包含各种各样的异构模型。模型间差异主要来源于训练数据分布、模型架构以及参数规模等因素。首先,不同模型在任务类型与专业领域上的性能存在显著差异。其次,模型之间存在形成内部集群的倾向。最后,不同模型在推理时延、推理成本以及上下文长度等效率与资源属性方面存在明显差异。如何定义模型之间的差异性对于匹配模型和任务至关重要。
现有研究通过在各领域的开源数据集上对模型按模型能力进行划分,例如Song等人[39]将能力定义为25个维度,然后根据各模型在不同任务上的表现进行人为判别打分。尽管能力区分模型在现有研究中被广泛应用并验证了其有效性,但是如何定义模型的异构性仍面临以下挑战:首先,业界对于如何划分统一的能力维度缺乏共识,难以形成有效的模型评估框架。此外,部分评估方法仍依赖人工干预,这不可避免地会引入主观偏差。最后,现有开源数据集的覆盖范围有限,难以全面覆盖所有专业领域。因此,如何定义模型异构是匹配任务的关键,缺乏异构性的共识已成为制约模型精准交互的重要瓶颈。
2)模型的协作方式
模型互联网集合了大量异构模型,所面临的任务类型丰富多样。因此,模型间的协作必须能够根据任务需求动态构建、实时适配。
现有研究多采用预设的固定模型与静态交互模式,主要聚焦于输出层面的集成策略,因而在动态任务场景下难以兼顾系统效率。例如,TETRIS方法[40]依赖专家模型进行持续指导,导致关键模型资源被长期占用,从而降低了整体系统的运行效率。现有协作方法多采用静态且无差别的权重分配策略,未能根据任务情境与模型输出的动态效用进行适配性调整。因此,现有研究难以直接迁移到动态变化的模型互联网中。
模型的动态性、任务的多样性及网络状态的不确定性,共同构成一个复杂的动态环境,直接影响协作效能。因此,模型间的自适应协作是提升模型互联网性能的关键因素。
3)模型的动态管理
系统动态性是模型互联网的核心特征,它体现为模型节点能够自由地接入与退出。这种“即插即用”的特性带来了显著优势:当部分模型因故障、维护、网络障碍或升级而无法服务时,系统能够通过快速调度其他可用模型来维持服务,从而保障用户的体验质量不受影响。模型的分布式更新与替换也在这一环境下得以高效实现。
然而,这种高度的动态性使得传统的静态配置与集中式管理范式完全失效。核心挑战在于:难以预设所有参与节点的状态,必须应对一个拓扑与能力节点实时演化的开放环境。A2A方法[41]通过让智能体在加入网络时提交一份“Agent Card”来对模型进行标签化管理。这种方法为模型的发现与筛选提供了便利,但其本质上依赖于模型的“自我报告”机制。该方案在一个开放、动态且可能存在竞争或恶意的环境中暴露出2个致命缺陷:其一,虚假的“Agent Card”会污染整个模型生态,从而影响系统整体服务质量;其二,当某些模型因网络拥塞、硬件故障或被动下线而无法使用时,系统若不能即时感知并更新其可用状态,会严重造成资源浪费。
因此,高效且自适应的动态管理是模型互联网的运行基石。它既是实现模型“自由接入、即插即用”的前提,更是确保全局服务质量与系统可靠性的根本保障。
4)隐私与安全问题
模型互联网促进模型间的交互与协作,但单个模型节点的安全漏洞可能通过协作关系在系统扩散。被攻陷的模型节点可成为攻击者在系统内部的切入点,利用信任关系向其他智能体传播恶意指令或虚假信息,这种现象被称为“传染效应”[42]。例如,串行协作通过在提示词中嵌入恶意提示诱导模型执行未授权的指令,从而导致整个系统的全面妥协[43]。此外,现有研究发现大模型能够从用户提示中获取敏感信息[44],而开放的模型互联网可能放大模型隐私泄露的风险。
要构建安全可信的模型互联生态环境,面临以下挑战:首先,如何甄别出恶意的模型从而在源头遏制恶意信息的传递;其次,如何保证交互时不泄露用户的敏感信息。面对上述挑战,未来的研究重心需从2个前沿展开攻坚:一方面,要发展出能实时识别并遏制恶意模型的动态防御体系;另一方面,必须攻克在复杂交互中保护数据隐私的关键技术,杜绝敏感信息泄露。这是迈向真正安全可信的模型互联网的必经之路。
5)异构模型互联互通
模型互联网在于构建一个泛在互联的模型网络群体,从而支持异构模型的高效传递和共享。然而,与互联网中的节点通信形式不同,模型互联网没有预先设定的通信链路,模型互联网的“连接”是瞬时、动态的软连接。此外,模型之间的组织形式也影响着模型路由的选择。
现有的多智能体通信协议在一定程度上为模型协作之间的通信提供了思路,但仍面临着挑战。例如,智能体通信协议(agent communication proposal,ACP)[45]是一种基于RESTful API的支持智能体通信开放标准。但在大规模部署的复杂场景下,该标准仍面临两大核心挑战:首先,缺乏动态协商、信息共享和模型协调的统一框架;其次,尚未建立跨域、可互认的信任体系以确保协作安全。
模型互联网旨在构建跨主体、跨平台的智能模型互联体系,实现模型之间的自由发现、自主协作与信息交换。因此,模型互联互通的研究不仅需要探讨模型间协作方式,还需要在协议层面建立通用、安全可信和高效的通信机制。
模型互联网是一种面向网络化人工智能模型的新范式。本文提出了模型互联网的概念、构想和层次结构,并搭建了相关原型系统。实验结果表明在精准度、稳定性、创造性和泛化性方面具有良好性能。模型互联网将探索模型间高效互联、智能互通、能力互补的新模式,以期推动大模型技术朝网络化方向发展,为人工智能领域研究提供新思路。此外,本文初步展望了模型互联网中富有潜力的研究方向,为深化与拓展模型互联网的研究提供了参考。

参考文献 引证文献
排序方式:
1
Berners-Lee T, Cailliau R, Luotonen A, et al. The world-wide web[J]. Communications of the ACM, 1994, 37(8): 76−82
2
Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [C] // Proc of the 31st Conf on Neural Information Processing Systems. New York: ACM, 2017: 6000–6010
3
Lin Luyuan, Wang Lingzhi, Guo Jinsong, et al. Investigating bias in LLM-based bias detection: Disparities between LLMs and human perception [C] //Proc of the 31st Int Conf on Computational Linguistics. Stroudsburg, PA: ACL, 2025: 10634−10649
4
苏金树. 领域定制方法促进网络与计算发展的思考[J]. 计算机研究与发展, 2025, 62(12): 2889−2894
Su Jinshu. Thinking on networking and computing promoted by domain-specific method[J]. Journal of Computer Research and Development, 2025, 62(12): 2889−2894 (in Chinese)
5
Feng Shagbin, Shi Weijia, Wang Yike, et al. Don’t hallucinate, abstain: Identifying LLM knowledge gaps via multi-LLM collaboration [C] //Proc of the 62nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2024: 14664−14690
6
Lu Zhicong, Li Jin, Li Peiguang, et al. Rethinking the reversal curse of LLMs: A prescription from human knowledge reversal [C] //Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 7518−7530
7
Shen Weizhou, Li Chenliang, Chen Hongzhan, et al. Small LLMs are weak tool learners: A multi-LLM agent [C] //Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 16658−16680
8
Hu Qitian J, Bieker J, Li Xiuyu, et al. ROUTERBENCH: A benchmark for multi-LLM routing system [J]. arXiv preprint, arXiv: 2403.12031, 2024
9
Agrawal A, Aralikatti R, Satheesh A, et al. Uncertainty-aware answer selection for improved reasoning in multi-LLM systems [C] //Proc of the Findings of the Association for Computational Linguistics (EMNLP 2025). Stroudsburg, PA: ACL, 2025: 25090−25098
10
Tang Liyan, Laban P, Durrett G. MiniCheck: Efficient fact-checking of LLMs on grounding documents[C]// Proc of the 2024 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2024: 8818–8847
11
Dong jing. China home to over one-third of world’s AI large language models [N/OL]. China Daily. (2024-07-03)[2026-01-01]. https://language.chinadaily.com.cn/a/202407/03/WS66850bcda31095c51c50c29e.html
Dong jing. China home to over one-third of world’s AI large language models [N/OL]. China Daily. (2024-07-03)[2026-01-01]. https://language.chinadaily.com.cn/a/202407/03/WS66850bcda31095c51c50c29e.html
12
He Na, Yan Yinging, Wu Ziyang, et al. Chat GPT-4 significantly surpasses GPT-3.5 in drug information queries[J]. Journal of Telemedicine and Telecare, 2025, 31(2): 306−308
13
Akhiad B, Itay L, Izik G, et al. Llama-nemotron: Efficient reasoning models [J]. arXiv preprint arXiv: 2505.00949, 2025
14
Deng Zehang, Ma Wanlun, Han Qinglong, et al. Exploring DeepSeek: A survey on advances, applications, challenges and future directions[J]. IEEE/CAA Journal of Automatica Sinica, 2025, 12(5): 872−893
15
Bai Shuai, Chen Keqin, Liu Xuejing, et al. Qwen2.5-vl technical report[J]. arXiv preprint arXiv: 2502.13923, 2025
16
Team Kimi, Du Angang, Yin Boohong, et al. Kimi-vl technical report[J]. arXiv preprint arXiv: 2504.07491, 2025
17
Aiersilan A, Liu Mingzhe. LLM-enhanced traffic editor for accelerated testing of autonomous vehicles under various pedestrian behaviors[C]//Proc of the 5th Int Conf on Smart Transportation and City Engineering. Bellingham, WA: SPIE, 2025, 13575: 1054−1060
18
Guan Yanchu, Wang Dong, Chu Zhixuan, et al. Intelligent agents with LLM-based process automation[C]// Proc of the 30th ACM SIGKDD Conf on Knowledge Discovery and Data Mining. New York: ACM, 2024: 5018−5027
19
Wu Shican, Ma Xiao, Luo Dehui, et al. Automated literature research and review-generation method based on large language models[J]. National Science Review, 2025, 12(6): nwaf169
20
Xu Derong, Zhang Ziheng, Zhu Zhihong, et al. Mitigating hallucinations of large language models in medical information extraction via contrastive decoding[C]// Proc of the Findings of the Association for Computational Linguistics (EMNLP 2024). Stroudsburg, PA: ACL, 2024: 7744−7757
21
Ma Mulei, Gong Chenyu, Zeng Liekang, et al. Multi-tier multi-node scheduling of LLM for collaborative AI computing[C]// Proc of the 2025 IEEE Conf on Computer Communications (IEEE INFOCOM 2025). Piscataway, NJ: IEEE, 2025: 1−10
22
Lu Jinliang, Pang Ziliang, Xiao Min, et al. Merge, ensemble, and cooperate! a survey on collaborative strategies in the era of large language models[J]. arXiv preprint arXiv: 2407.06089, 2024
23
Yadav P, Tam D, Choshen L, et al. Ties-Merging: Resolving interference when merging models[J]. Advances in Neural Information Processing Systems, 2023, 36: 7093−7115
24
Lu Zheyi, Fan Chenghao, Wei Wei, et al. Twin-Merging: Dynamic integration of modular expertise in model merging[J]. Advances in Neural Information Processing Systems, 2024, 37: 78905−78935
25
Huang Yichong, Feng Xiaocheng, Li Baohang, et al. Ensemble learning for heterogeneous large language models with deep parallel collaboration[J]. Advances in Neural Information Processing Systems, 2024, 37: 119838−119860
26
王建辉, 李哲涛, 伍涛, 等. Token级多模型并联协作推理[J]. 计算机学报, 2025, 48(11): 2579−2593
Wang Jianhui, Li Zhetao, Wu Tao, et al. Token-level collaborative reasoning for parallel multi-models[J]. Chinese Journal of Computers, 2025, 48(11): 2579−2593 (in Chinese)
27
吴俊儒, 李哲涛, 王建辉, 等. 基于协作关系的模型动态路由. [J/OL]. 软件学报, 2025[2026-01-02]. http: //www.jos.org.cn/1000-9825/7498.html
Wu Junru, Li Zhetao, Wang Jianhui, et al. Dynamic model routing based on collaborative relationship [J/OL]. Journal of Software, 2025[2026-01-02]. http://www.jos.org.cn/1000-9825/7498.html (in Chinese)
28
Pan Shirui, Luo Linhao, Wang Yufei, et al. Unifying large language models and knowledge graphs: A roadmap[J]. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(7): 3580−3599
29
Wu Weiqi, Wu Hongqiu, Jiang Lai, et al. From role-play to drama-interaction: An LLM solution [C]// Proc of the Findings of the Association for Computational Linguistics (ACL 2024 ). Stroudsburg, PA: ACL, 2024: 3271−3290
30
Ong I, Almahairi A, Wu V, et al. RouteLLM: Learning to route LLMs with preference data[J]. arXiv preprint arXiv: 2406.18665, 2024
31
Ding Dujian, Mallick A, Zhang Shaokun, et al. BEST-Route: Adaptive LLM routing with test-time optimal compute[C/OL]// Proc of the 42nd Int Conf on Machine Learning. New York: ACM, 2025[2026-01-03]. https://openreview.net/forum?id=tFBIbCVXkG
32
Feng Tao, Shen Yanzhen, You Jiaxuan. GraphRouter: A graph-based router for LLM selections[C/OL]// Proc of the 13th Int Conf on Learning Representations. New York: ACM, 2025[2026-01-03]. https://openreview.net/forum?id=eU39PDsZtT
33
Liu Jun, Kong Zhenglun, Yang Changdi, et al. RCR-Router: Efficient role-aware context routing for multi-agent LLM systems with structured memory[J]. arXiv preprint, arXiv: 2508.04903, 2025
34
Stripelis D, Xu Zhaozhou, Hu Zijian, et al. TensorOpera router: A multi-model router for efficient LLM inference[C]// Proc of the 2024 Conf on Empirical Methods in Natural Language Processing (EMNLP 2024). Stroudsburg, PA: ACL, 2024: 452−462
35
Du Yilun, Li Shuang, Torralba A, et al. Improving factuality and reasoning in language models through multiagent debate[C]//Proc of the 41st Int Conf on Machine Learning. New York: ACM, 2024: 11733−11763
36
Huang Yuzhen, Bai Yuzhou, Zhu Zhihao, et al. C-Eval: A multi-level multi-discipline Chinese evaluation suite for foundation models [C]// Proc of the 37th Conf on Neural Information Processing Systems (NeurIPS 2023). New York: ACM, 2023: 62991−63010
37
Clark C, Lee K, Chang Mingwei, et al. BoolQ: Exploring the surprising difficulty of natural yes/no questions[C]// Proc of the 2019 Conf of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, PA: ACL, 2019: 2924−2936
38
Hendrycks D, Burns C, Basart S, et al. Measuring massive multitask language understanding[J]. arXiv preprint arXiv: 2009.03300, 2020
39
Song Wei, Huang Zhenya, Cheng Cheng, et al. IRT-Router: Effective and interpretable multi-LLM routing via item response theory[C]// Proc of the 63rd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2025: 15629−15644
40
Wu Zhaoxuan, Zhou Zijian, Verma1 A, et al. TETRIS: Optimal draft token selection for batch speculative decoding. [C]// Proc of the 63rd Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2025: 33329−33345
41
Rao S, Philip S. Announcing the agent2agent protocol (A2A)[EB/OL]. 2025[2025-10-19]. https://developers.googleblog.com/en/a2a-a-new-era-of-agent-interoperability/
42
Liu Yuhan, Song Zirui, Zhang Juntian, et al. The stepwise deception: Simulating the evolution from true news to fake news with LLM agents[C]// Proc of the 2025 Conf on Empirical Methods in Natural Language Processing. Stroudsburg, PA: ACL, 2025: 26187−26203
43
Yu Miao, Meng Fanci, Zhou Xinyun, et al. A survey on trustworthy LLM agents: Threats and countermeasures[C]// Proc of the 31st ACM SIGKDD Conf on Knowledge Discovery and Data Mining V.2. New York: ACM, 2025: 6216−6226
44
Zhang Xiaojin, Pang Yahao, Kang Yan, et al. No free lunch theorem for privacy-preserving LLM inference[J]. Artificial Intelligence, 2025, 341: 104293
45
IBM BeeAI. Introduction to agent communication protocol (ACP). [EB/OL] (2024-12-03)[2026-01-03]. https://docs.beeai.dev/acp/alpha/introduction
2026年第63卷第5期
55
23
0
引用本文
BibTeX
文章信息
doi: 10.7544/issn1000-1239.202550223
  • 接收时间:2025-03-24
  • 首发时间:2026-11-17
  • 出版时间:2026-05-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-03-24
  • 修回日期:2026-01-19
  • 录用日期:2026-01-29
基金
作者信息
    暨南大学信息科学技术学院 广州 510632
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202550223
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏