RESEARCH PAPERS

Research on Collaborative Pathways of Library Multi-Agent Systems from the Perspective of Collaborative Intelligence Theory

  • Guo Limin ,
  • Fu Yaming ,
  • Liu Yueru
Expand
  • 1 Shanghai Library/Institute of Scientific & Technical Information of Shanghai, Shanghai 200031;
    2 School of Cultural Heritage and Information Management, Shanghai University, Shanghai 200444;
    3 Tongji University Library, Shanghai 200092
Wang Yuxia, Master’s Candidate; Han Yi, Professor, PhD, Corresponding Author, E-mail: hanyi72@swu.edu.cn.

Received date: 2025-08-01

  Revised date: 2025-11-11

  Online published: 2026-05-22

Supported by

This work is supported by the youth project of Humanities and Social Sciences Research by the Ministry of Education, titled “Research on Narrative Models and Trustworthy Governance of Digital Cultural Heritage Based on Generative Artificial Intelligence” (Grant No. 25YTCZH049); and the Shanghai Library (Institute of Scientific & Technical Information of Shanghai) “2151”Human Resources CapacityBuilding Program Core Talent Project titled “Research on the Application of Multimodal Recommendation Systems in Libraries.”

Abstract

[Purpose/Significance] With large language models driving a paradigm shift toward agentic AI, multi-agent systems—owing to their strengths in task decomposition, semantic orchestration, and role coordination—are increasingly emerging as a new direction for the intelligence development of libraries. This paper aims to develop a multi-agent collaboration framework applicable to library services, explore its composition and application pathways, and provide theoretical support for smart library construction. [Method/Process] Grounded in collaborative intelligence theory, this study combines structural modeling with scenario analysis to design a library multi-agent system architecture. It proposes a five-dimensional model encompassing role functions, collaboration mechanisms, communication protocols, organizational structure, and task strategies. Furthermore, it conducts an application analysis in typical service scenarios such as information retrieval, reference consultation, and resource recommendation. Research topics and practical suggestions are subsequently presented. [Result/Conclusion] Multiagent systems represent a key practical form of agentic AI in the library domain. This paper systematically proposes a library-oriented multi-agent collaborative framework and application schemes, aiming to provide theoretical support and extended research directions for the construction of intelligent service systems.

Cite this article

Guo Limin , Fu Yaming , Liu Yueru . Research on Collaborative Pathways of Library Multi-Agent Systems from the Perspective of Collaborative Intelligence Theory[J]. Library and Information Service, 2026 , 70(11) : 125 -136 . DOI: 10.13266/j.issn.0252-3116.2026.11.010

References

[1] 张晓林. Library-Inside:AI赋能图书馆新质生产力的一种基础模型[J].中国图书馆学报, 2024, 50(3):4-16.(ZHANG X L. Library-Inside:a foundation model for AI-empowered new quality productive forces for library services[J]. Journal of library science in China, 2024, 50(3):4-16.)
[2] 郭亚军,寇旭颍,冯思倩,等.大语言模型赋能图书馆参考咨询服务:逻辑、场景与体系[J].图书馆论坛, 2025, 45(1):118-127.(GUO Y J, KOU X Y, FENG S Q, et al. Large language model empowers library reference services:logic, scenarios, and framework[J]. Library tribune, 2025, 45(1):118-127.)
[3] 罗燚,李广通,何杰. DeepSeek赋能图书馆参考咨询服务的路径[J].图书馆论坛, 2025, 45(6):133-140.(LUO Y, LI G T, HE J. The path for DeepSeek to empower library reference services[J]. Library tribune, 2025, 45(6):133-140.)
[4] 刘崧印,朱学芳,王震宇.基于大语言模型的书目检索系统设计与实现[J].图书馆论坛, 2025, 45(7):113-120.(LIU S Y, ZHU X F, WANG Z Y. Design and implementation of bibliographic retrieval system based on large language model[J].Library tribune, 2025, 45(7):113-120.)
[5] 黄永文,马玮璐,鲜国建等.大语言模型驱动的科学数据自动分类研究[J].情报理论与实践, 2025, 48(6):170-177, 194.(HUANG Y W, MA W L, XIAN G J, et al. Large language modeldriven automated classification of scientific data[J]. Information studies:theory&application, 2025, 48(6):170-177, 194.)
[6] 张卫东,陈希鹏,翁慧诠.基于大模型与LoRA的东北抗联红色人物知识图谱构建方法研究[J].情报理论与实践,2025, 48(8):187-195.(ZHANG W D, CHEN X P, WENG H Q.A knowledge graph construction method for Northeast CounterJapanese United Army red figures based on LLM and Lo RA fine-tuning[J]. Information studies:theory&application, 2025,48(8):187-195.)
[7] 李明,罗晓兰,朱邦贤.中医古籍方剂数据挖掘与知识问答系统构建[J].图书馆论坛, 2025, 45(4):49-59.(LI M, LUO X L, ZHU B X. Data mining and knowledge Q&A system for traditional Chinese medicine formulas in ancient books[J].Library tribune, 2025, 45(4):49-59.)
[8] 郭利敏,付雅明.融合ReAct模式的图书馆大语言模型知识服务系统构建[J].图书馆论坛, 2024, 44(6):61-70.(GUO L M,FU Y M. An LLM-based knowledge service system for libraries integrating the ReAct model[J]. Library tribune, 2024, 44(6):61-70.)
[9] 赵宇翔,付振康,曾鹏翔,等.生成式人工智能驱动下智慧图书馆信息搜索的技术框架及服务模式研究[J].中国图书馆学报, 2025, 51(5):54-66.(ZHAO Y X, FU Z K, ZENG P X, et al. Technological framework and service model of information search in smart libraries:a generative artificial intelligence perspective[J]. Journal of library science in China, 2025, 51(5):54-66.)
[10] CHEN X, LI Y, CAI H, et al. Multi-agent proactive information seeking with adaptive LLM orchestration for non-factoid question answering[C]//Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V. 2. New York:ACM, 2025:4341-4352.
[11] 祝嘉淇,孟高慧,刘畅,等.迈向智慧图书馆:图书馆管理系统的智慧化赋能方案设计[J].图书情报知识, 2024, 41(6):64-74.(ZHU J Q, MENG G H, LIU C, et al. Toward smart libraries:a smart empowerment scheme design for library management systems[J]. Documentation, information&knowledge, 2024,41(6):64-74.)
[12] 李书宁,刘一鸣. ChatGPT类智能对话工具兴起对图书馆行业的机遇与挑战[J].图书馆论坛, 2023, 43(5):104-110.(LI S N, LIU Y M. Opportunities and challenges for library from the rise of ChatGPT-like intelligent chat tools[J]. Library tribune,2023, 43(5):104-110.)
[13] PARK J S, O'BRIEN J, CAI C J, et al. Generative agents:Interactive simulacra of human behavior[C]//Proceedings of the 36th annual acm symposium on user interface software and technology. New York:ACM, 2023:1-22.
[14] CHEN W, SU Y, ZUO J, et al. Agentverse:facilitating multiagent collaboration and exploring emergent behaviors in agents[J]. arXiv preprint arXiv:2308.10848
[15] JIN W, DU H, ZHAO B, et al. A comprehensive survey on multiagent cooperative decision-making:scenarios, approaches,challenges and perspectives[J]. arXiv preprint arXiv:2503.13415,2025.
[16] SCHLEIGER E, MASON C, NAUGHTIN C, et al. Collaborative intelligence:a scoping review of current applications[J]. Applied artificial intelligence, 2024, 38(1):2327890.
[17] 郭利敏,付雅明,刘悦如.检索增强思维在图书馆知识挖掘服务中的应用研究[J].图书情报工作, 2025, 69(21):108-119.(GUO L M, FU Y M, LIU Y R. Research on the application of retrieval augmented thoughts in library knowledge mining services[J]. Library and information service, 2025, 69(21):108-119.)
[18] 郭利敏,张磊. FOLIO的技术选型与运营模式研究[J].中国图书馆学报, 2020, 46(1):92-98.(GUO L M, ZHANG L.Technology selection and operation mode of FOLIO[J]. Journal of library science in China, 2020, 46(1):92-98.)
[19] WOOLDRIDGE M. An introduction to multiagent systems[M].Hoboken:John wiley&sons, 2009.
[20] WOOLLEY A W, CHABRIS C F, PENTLAND A, et al.Evidence for a collective intelligence factor in the performance of human groups[J]. science, 2010, 330(6004):686-688.
[21] GUO T, CHEN X, WANG Y, et al. Large language model based multi-agents:a survey of progress and challenges[J]. arXiv preprint arXiv:2402.01680, 2024.
[22] MILLER J H, PAGE S E. Complex adaptive systems:an introduction to computational models of social life:an introduction to computational models of social life[M].Princeton:Princeton University Press, 2009.
[23] SUN C, HUANG S, POMPILI D. Llm-based multi-agent reinforcement learning:current and future directions[J]. arXiv preprint arXiv:2405.11106, 2024.
[24] HATALIS K, CHRISTOU D, MYERS J, et al. Memory matters:the need to improve long-term memory in llm-agents[C]//Proceedings of the AAAI Symposium Series. Washington:AAAI,2023, 2(1):277-280.
[25] ZHANG Z, BO X, MA C, et al. A survey on the memory mechanism of large language model based agents[J]. arXiv preprint arXiv:2404.13501, 2024.
[26] HUANG X, LIU W, CHEN X, et al. Understanding the planning of LLM agents:a survey[J]. arXiv preprint arXiv:2402.02716,2024.
[27] DAFOE A, BACHRACH Y, HADFIELD G, et al. Cooperative AI:machines must learn to find common ground[J]. Nature,2021, 593(7857):33-36.
[28] TRAN K T, DAO D, NGUYEN M D, et al. Multi-agent collaboration mechanisms:a survey of LLMs[J]. arXiv preprint arXiv:2501.06322, 2025.
[29] DE BAYSER M G, CAVALIN P, PINHANEZ C, et al. Learning multi-party turn-taking models from dialogue logs[J]. arXiv preprint arXiv:1907.02090, 2019.
[30] STEWART R, PALMER T S, BAYS S. An agent-based blackboard system for multi-objective optimization[J]. Journal of computational design and engineering, 2022, 9(2):480-506.
[31] BENEDIKT KAESBERG L, BECKER J, WAHLE J P, et al.Voting or consensus?Decision-making in multi-agent debate[J].arXiv preprint arXiv:2502.19130, 2025.
[32] FENG Y, LU Z, LIU B, Et al. Towards LLM-driven dialogue state tracking[J]. arXiv preprint arXiv:2310.14970, 2023.
[33] QIAN C, LIU W, LIU H, ET al. Chatdev:communicative agents for software development[J]. arXiv preprint arXiv:2307.07924,2023.
[34] HAN S, ZHANG Q, YAO Y, et al. LLM multi-agent systems:challenges and open problems[J]. arXiv preprint arXiv:2402.03578, 2024.
[35] GUO T, CHEN X, WANG Y, et al. Large language model based multi-agents:a survey of progress and challenges[J]. arXiv preprint arXiv:2402.01680, 2024.
[36] 郭利敏,付雅明.以大语言模型构建智慧图书馆:框架和未来[J].图书馆杂志, 2023, 42(11):22-30, 133.(GUO L M,FU Y M. Building smart libraries with large language model:frameworks and the future[J]. Library journal, 2023, 42(11):22-30, 133.)
Outlines

/

〈 〉