图书馆学智能体概念的跨学科比较与协同范式研究

doi:10.13998/j.cnki.issn1002-1248.25-0385

摘要/Abstract

摘要：

[目的/意义] 通过跨学科比较揭示智能体概念的核心内涵、共性内核与领域分化，揭示图书馆学蕴含的智能体相关概念和理论，并分析大语言模型驱动的AI Agent对图书馆核心服务的革新价值，推动知识服务向智能化、协同化范式转型。 [方法/过程] 采用跨学科文献分析法，梳理哲学、经济学、法律、生物学、社会学、计算机科学六大学科中智能体的名词定义、理论演进与应用特征，发掘图书馆学中蕴含与智能体相关的概念和理论，对比各学科智能体在自主性、感知性、目的性、适应性、交互性五维特性的共性与分化，将六大学科理论精髓映射至图书馆学实务场域中三元主体，解析读者、馆员、系统的智能体角色协同机制。 [结果/结论] 跨学科智能体共性围绕自主行为体在环境中实现目标展开，五维特性构成跨学科共识，差异源于学科核心问题；图书馆本质是多智能体系统，读者智能体融合哲学意向性与经济学博弈策略，体现需求驱动的适应性检索，馆员智能体继承法律代理权责与社会学结构能动性，成为资源与用户的专业中介，系统Agent借鉴生物学演化适应与计算机感知闭环，进阶为自主优化的智能基座。AI Agent是对图书馆学固有智能体特性的技术增强，通过大语言模型实现自动化、个性化与智能化服务升级，实现意图理解、工具调用、多智能体协作，驱动三元主体从被动响应转向主动协同。首创图书馆学三元智能体框架，明确读者、馆员、系统的协同智能体角色，揭示大语言模型驱动的AI Agent与图书馆学的深层契合逻辑。

关键词: 图书馆学, 人工智能, 智能体, 跨学科研究, 人机协同

Abstract:

[Purpose/Significance] Through interdisciplinary comparison, the core connotation, common core and field differentiation of the Agent concept are revealed, the Agent-related concepts and theories contained in library science are revealed, and the innovative value of AI Agent driven by large language models to the core services of libraries is analyzed to promote the transformation of knowledge services to intelligent and collaborative paradigms. Understanding the interdisciplinary nature of Agents will help library science, information science and other related disciplines to better design and apply AI technologies and achieve the core mission of connecting humans and knowledge in a more efficient, accurate and humane way. It will also enable library science to more accurately integrate the essence of the six major disciplines and transform the traditional three-subject relationship of readers, librarians and systems into a new collaborative paradigm. [Method/Process] Using interdisciplinary literature analysis, the definition, theoretical evolution and application characteristics of Agent in six major disciplines of philosophy, economics, law, biology, sociology and computer science are sorted out, the concepts and theories related to Agent contained in library science are explored, and the commonalities and differentiation of Agent in the five-dimensional characteristics of autonomy, perception, purpose, adaptability and interactivity of each discipline are compared. The theoretical essence of the six major disciplines is mapped to the three-dimensional subject in the practical field of library science, and the Agent role coordination mechanism of readers, librarians and systems is analyzed. Readers are entities with intentions and autonomous consciousness, and they will actively initiate information search behaviors based on information needs such as learning knowledge and solving problems and will also adjust their strategies according to environmental changes such as technical tools and social culture, reflecting agent-like adaptability. Librarians serve as service intermediaries and information gatekeepers, connecting readers with resources through technical services such as classification and cataloging, and helping users clarify their information needs and improve their information literacy through reader services such as reference consultation. The library's information systems will also simulate human agent capabilities through algorithms or technologies. Automated search engines or crawlers will collect data according to preset rules, and personalized information recommendations will be made based on user behavior, driving the library's management and services towards automation and intelligence. [Results/Conclusions] The commonality of interdisciplinary agents revolves around the realization of goals by autonomous actors in the environment. The five-dimensional characteristics constitute an interdisciplinary consensus, and the differences are due to the core issues of the disciplines. The essence of a library is a multi-agent system. The reader agent integrates philosophical intentionality and economic game strategy, reflecting demand-driven adaptive retrieval. The librarian agent inherits the legal agency rights and responsibilities and the sociological structural initiative, becoming a professional intermediary between resources and users. The system agent draws on the biological evolutionary adaptation and computer perception closed loop, and advances to an intelligent base for autonomous optimization. AI Agent is a technical enhancement of the inherent agent characteristics of library science. It realizes automation, personalization and intelligent service upgrades through large language models, realizes intention understanding, tool calling, and multi-agent collaboration, and drives the three-element subject from passive response to active collaboration. The three-element agent framework for library science is created, which clarifies the collaborative agent roles of readers, librarians, and systems, and reveals the deep logic of AI Agent driven by large language models and library science. An interdisciplinary comparative study of the Agent concepts reveals that its essence is a practical vehicle for achieving autonomous decision-making in a specific environment. Philosophy gives it depth of consciousness, economics models strategic games, law defines the boundaries of rights and responsibilities, biology reveals evolutionary logic, sociology anchors structural interactions, and computer science ultimately achieves a closed-loop technology. Library science constructs a ternary collaborative intelligent ecosystem that transforms abstract autonomy into a practical paradigm of knowledge connection through the dynamic collaboration of readers, librarians, and systems.

Key words: library science, artificial intelligence, AI Agent, interdisciplinary research, human-AI collaboration

中图分类号: G250.7

陈嘉勇, 龚蛟腾, 王彧弋. 图书馆学智能体概念的跨学科比较与协同范式研究[J]. 农业图书情报学报, 2025, 37(5): 27-39.

CHEN Jiayong, GONG Jiaoteng, WANG Yuyi. Research of Interdisciplinary Comparison and Collaborative Paradigm on the Concept of Agent in Library Science[J]. Journal of library and information science in agriculture, 2025, 37(5): 27-39.

图/表 3

表1

Agent概念在不同学科领域中的译名、定义、特性侧重、经典文献、相关理论与应用场景"

领域	译名	定义	特性侧重	经典文献	相关理论	应用场景
哲学	行为主体	拥有欲望、信念、意图及行动能力的实体	自主性目的性（强调意图驱动理性决策）	BRATMAN（1987）； DENNETT（2004）； SEARLE（1986）	BDI模型意向性理论演化适应性理论	人类行为建模人工智能伦理
经济学	经济主体	参与经济活动的决策实体，在约束条件下追求效用或利润最大化	目的性适应性（侧重目标导向与策略调整）	VON NEUMANN & MORGENSTERN（1944）； HARSANYI（1967）； KAHNEMAN & TVERSKY（1979）	完全理性模型贝叶斯博弈论展望理论	市场竞争分析拍卖机制设计行为金融与公共政策
法律	代理人	被授权代表委托人行使权利并承担法律后果的实体	交互性自主性（聚焦授权关系下的协作行为）	《中华人民共和国民法典》第161~175条； Restatement (Third) of Agency（2006）； POSNER（1973）	委托代理理论法律激励系统	合同签订公司治理诉讼代理专利代理房产中介品牌经销
生物学	适应主体	具有生存策略的生物个体或群体，通过自然选择优化基因传播	适应性感知性（关注环境反馈与无意识演化）	DAWKINS（1976）； SMITH（1982）； LEVIN（1998）	自私基因理论演化稳定策略多层次互动涌现	基因编辑工具动物行为解释群体智能
社会学	行动者	具有意图、反思能力并能主动塑造社会结构的个体或集体实体	交互性自主性（突出社会网络中的实践能力）	WEBER（1936）； PARSONS（1968）； LATOUR（2005）	社会行动理论结构能动性理论非人类行动者网络	社会变迁研究制度设计
计算机科学	智能体	通过传感器感知环境、执行器影响环境，具有自主决策能力的软件实体	自主性感知性适应性（全栈覆盖感知-行动闭环）	TURING（1950） RUSSELL & NORVIG（1995）； YAO（2023）	BDI计算模型感知规划决策执行循环多智能体系统	自动化系统聊天机器人自动驾驶系统虚拟社会模拟软件开发协作
图书馆学	协同主体	实现知识连接的读者、馆员、系统三元协同主体，通过人机协作优化信息获取效率	目的性交互性适应性（强调知识传递目标下的动态协作）	TAYLOR（1967）；ELLIS（1989）；DERVIN（1992）	信息搜寻模型意义建构理论信息需求层次理论	读者主动搜寻馆员参考咨询信息检索系统

表1

表2

表3

参考文献 35

[1]	MCCANN H J, BRATMAN M E. Intention, plans, and practical reason[J]. Noûs, 1991, 25(2): 230.
[2]	刘炜. 大模型与智能体[J]. 图书情报知识, 2025, 42(2): 1.
	LIU W. Large model and agent[J]. Documentation, information & knowledge, 2025, 42(2): 1.
[3]	SEARLE J R. Minds, brains and science[M]. Cambridge, United States: Harvard University Press, 1986.
[4]	DENNETT D C. Freedom evolves[M]. London: Penguin, 2004.
[5]	SEARLE J R. Intentionality[M]. Cambridge, UK: Cambridge University Press, 1983.
[6]	VON NEUMANN J, MORGENSTERN O. Theory of games and economic behavior[M]. Princeton: Princeton University Press, 1944.
[7]	HARSANYI J C. Games with incomplete information played by "Bayesian" players, I–III: Part I. The basic model[J]. Management science, 2004, 50(ement): 1804-1817.
[8]	KAHNEMAN D, TVERSKY A. Prospect theory: An analysis of decision under risk[J]. Econometrica, 1979, 47(2): 263.
[9]	中华人民共和国民法典[EB/OL]. [2025-06-20]. .
[10]	American Law Institute. Restatement (Third) of Agency[M]. Philadelphia: American Law Institute, 2006.
[11]	POSNER R. Economic analysis of law[M]. Boston: Little Brown and Company, 1973.
[12]	DAWKINS R. The selfish gene[M]. Oxford: Oxford University Press, 1976.
[13]	WILLIAMS G C. Adaptation and natural selection: A critique of some current evolutionary thought[M]. Princeton: Princeton University Press, 2018.
[14]	SMITH J M. Evolution and the theory of games[M]//Did Darwin Get It Right? Boston, MA: Springer US, 1988: 202-215.
[15]	LEVIN S A. Ecosystems and the biosphere as complex adaptive systems[J]. Ecosystems, 1998, 1(5): 431-436.
[16]	WEBER M. Social action[M]. Thousand Oaks: Sage Publication, 1936.
[17]	WIRTH L, PARSONS T. The structure of social action: A study in social theory with special reference to a group of recent European writers[J]. American sociological review, 1939, 4(3): 399.
[18]	LATOUR B. Reassembling the social: An introduction to actor-network-theory[M]. Oxford: Oxford University Press, 2005.
[19]	TURING A M. Computing machinery and intelligence[M]//Parsing the Turing Test. Dordrecht: Springer Netherlands, 2007: 23-65.
[20]	BROOKS R. A robust layered control system for a mobile robot[J]. IEEE journal on robotics and automation, 1986, 2(1): 14-23.
[21]	BROOKS R A. Intelligence without representation[J]. Artificial intelligence, 1991, 47(1/2/3): 139-159.
[22]	COHEN P R, LEVESQUE H J. Intention is choice with commitment[J]. Artificial intelligence, 1990, 42(2/3): 213-261.
[23]	RUSSELL S J, NORVIG P. Artificial intelligence: A modern approach[M]. London: Pearson, 1995.
[24]	WOOLDRIDGE M, JENNINGS N R. Intelligent agents: Theory and practice[J]. The knowledge engineering review, 1995, 10(2): 115-152.
[25]	WEI J, WANG X, SCHUURMANS D, et al. Chain-of-thought prompting elicits reasoning in large language models[C]//Advances in Neural Information Processing Systems. New Orleans: NeurIPS, 2022: 24824-24837.
[26]	YAO S, ZHAO J, YU D, et al. React: Synergizing reasoning and acting in language models[C]//International Conference on Learning Representations (ICLR). Kigali: OpenReview, 2023.
[27]	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. San Francisco CA USA: ACM, 2023: 1-22.
[28]	QIAN C, LIU W, LIU H, et al. Chatdev: Communicative agents for software development[J/OL]. arXiv preprint arXiv:, 2023.
[29]	XI Z H, CHEN W X, GUO X, et al. The rise and potential of large language model based agents: A survey[J]. Science China information sciences, 2025, 68(2): 121101.
[30]	WIESINGER J, MARLOW P, VUSKOVIC V. Agents[EB/OL]. [2024-09-02]. .
[31]	ELLIS D. A behavioural approach to information retrieval system design[J]. Journal of documentation, 1989, 45(3): 171-212.
[32]	DERVIN B. From the mind's eye of the user: The sense-making qualitative-quantitative methodology[J]. Qualitative research in information management, 1992, 9(1): 61-84.
[33]	TAYLOR, ROBERT S. Question-negotiation an information-seeking in libraries[M]. Bethlehem, PA: Lehigh University Center for Information Science, 1967.
[34]	PIAGET J. The role of action in the development of thinking. In Knowledge and Development: Volume 1 Advances in Research and Theory. Boston, MA: Springer
[35]	MINSKY M. Society of mind[M]. New York: Simon and Schuster, 1986.

领域	典型实体	定义	自主性	感知性	目的性	适应性	交互性
哲学	人类	拥有欲望、信念、意图的意识实体	理性主体意志与反思能力	意识驱动的环境理解	欲望信念意图目标	动态调整计划	多主体协作承诺
经济学	消费者企业政府	追求效用或利润最大化的决策实体	约束条件下的效用最大化决策	市场信号与信息不对称识别	利润效用最大化	策略随博弈环境演化	寡头竞争/拍卖交互
法律	法律代理人经纪人	被授权代表委托人的责任实体	委托人授权下的代理行为	法律条款与权责关系识别	实现委托目标和契约义务	监管约束、合规性调整	委托人-代理人-第三方关系链
生物学	基因生物个体生物种群	基因驱动的无意识适应主体	基因驱动的无意识生存决策	环境压力与资源竞争感知	生存与繁殖成功率最大化	演化稳定策略	种群竞争和共生
社会学	个人社会组织	结构约束下的能动实践者	结构制约中的能动性	社会规范与文化语境识别	意义赋予与资源争夺	策略性适应社会变迁	社会网络互动
计算机科学	软件智能体机器人	感知环境并执行行动的软件代理	算法驱动的任务自主执行	传感器数据与环境状态获取	预设任务优化	机器学习反馈调优	多Agent系统协作
图书馆学	读者馆员系统	信息寻求者专业中介者技术执行者	需求主导检索专业判断决策规则自动化执行	用户行为数据资源元数据系统状态监控	解决信息需求资源精准匹配服务效率优化	响应用户行为变化适配技术生态演进	读者馆员参考咨询读者系统信息检索馆员系统信息组织

学科领域	核心理论贡献	图书馆学映射
哲学	理性决策与意向性本质	用户意图驱动的信息搜寻逻辑
经济学	有限理性下的策略博弈	资源分配中的效用最大化机制
法律	权责明晰的代理关系	馆员服务的授权与责任边界
生物学	无意识演化的群体适应性	信息系统自我优化的反馈循环
社会学	结构约束中的能动实践	用户、馆员、系统的社会网络协同
计算机科学	感知决策行动的技术闭环	AI Agent的全栈智能化支撑