图书情报工作

图书情报工作 >

2025 , Vol. 69 >Issue 17: 3 - 15

DOI: https://doi.org/10.13266/j.issn.0252-3116.2025.17.001

专稿

从管理信息系统到情报智能体：重塑科技情报工作范式

  • 刘细文 ,
  • 孙蒙鸽 ,
  • 付芸
展开
  • 1 中国科学院文献情报中心 北京 100190;
    2 中国科学院大学经济与管理学院信息资源管理系 北京 100049
刘细文，研究员，博士生导师；孙蒙鸽，博士研究生；付芸，馆员，博士，通信作者，E-mail: fuy@mail.las.ac.cn.

收稿日期: 2025-06-01

  修回日期: 2025-06-22

  网络出版日期: 2025-08-20

基金资助

本文系国家社会科学基金重大项目“数智转型背景下智能情报关键技术应用研究”（项目编号：23&ZD228）研究成果之一。

收起

From MIS to DIS Agent: Reshaping the Paradigm of S&T Documentation and Information Service

  • Liu Xiwen ,
  • Sun Mengge ,
  • Fu Yun
Expand
  • 1 National Science Library, Chinese Academy of Sciences, Beijing 100190;
    2 Department of Information Resources Management, School of Economics and Management, University of Chinese Academy of Sciences, Beijing 100049
Liu Xiwen, Research Fellow, Doctoral Supervisor; Sun Mengge, Doctoral Candidate; Fu Yun, Librarian, PhD, Corresponding Author, E-mail: fuy@mail.las.ac.cn.

Received date: 2025-06-01

  Revised date: 2025-06-22

  Online published: 2025-08-20

Supported by

This work is supported by major program of National Social Science Fund of China titled “Research on the Application of Key Technologies for Intelligent Information in the Context of Digital-Intelligent Transformation” (Grant No. 23&ZD228).

Fold

摘要

[目的/意义] 探讨智能体（Agent）在科技情报工作中的适配性与演进路径，回应科技情报工作日益增长的智能化和协同化需求，揭示“情报智能体”（documentation and information service agent, DIS Agent）构建的理论基础与系统机制，为情报系统向更高层级情报认知能力演进提供方法论支撑。[方法/过程] 基于智能体能力分级与多智能体协作模式，梳理其在科研与情报工作中的迭代路径，结合情报学的信息管理、情报分析和交流传播三大研究范畴，提出科技情报工作由管理信息系统（management information system, MIS），经AI Agent系统，迈向Agentic AI范式的三阶段跃迁路径；提出以“任务闭环”为核心的智能体情报系统结构，并阐释“人—多智能体协同”机制的形成基础与演化逻辑。[结果/结论] 情报智能体是一种以大语言模型为认知中枢、集成多类型智能体模块的任务型系统形态，具备模块化结构与协同演化能力。在该系统支持下，信息管理、情报分析与交流传播三类情报研究实现了从规则配置到语义驱动的系统跃迁，表现为任务驱动的知识组织、自主化策略生成与传播闭环优化等能力提升。与此同时，情报专家的角色由操作主体转变为“情报任务框架设定者”与“过程质量监督者”，系统运行逻辑转向“人—多智能体协同”新范式。未来将据此推进情报智能体系统的研发与应用验证。

关键词： 情报智能体; 管理信息系统; 人—多智能体协同; 科技情报工作; 新范式

本文引用格式

刘细文 , 孙蒙鸽 , 付芸 . 从管理信息系统到情报智能体：重塑科技情报工作范式[J]. 图书情报工作, 2025 , 69(17) : 3 -15 . DOI: 10.13266/j.issn.0252-3116.2025.17.001

Abstract

[Purpose/Significance] This study investigates the adaptability and evolutionary path of agent technologies in science and technology (S&T) intelligence work, aiming to meet the increasing demands for intelligent and collaborative systems. It introduces the concept of the Documentation and Information Service Agent (DIS Agent) and clarifies its theoretical foundation and system mechanisms, providing methodological support for advancing S&T intelligence systems toward higher-level cognitive capabilities. [Method/Process] Drawing on the stratification of agent capabilities and multi-agent collaboration models, the study examines their development in scientific and intelligence contexts. It proposes a three-stage system evolution path—from Management Information Systems (MIS), through AI Agent systems, to the Agentic AI paradigm—within the three major domains of information management, intelligence analysis, and scholarly communication. A task-closed-loop architecture is proposed to support the emergence of human–multi-agent collaboration mechanisms. [Result/Conclusion] DIS Agents are task-oriented systems that integrate multiple types of agents with large language models as cognitive cores, characterized by modular design and collaborative evolution capabilities. Under this architecture, the three core domains of intelligence work undergo a shift from rule-based configuration to semantic-driven systems, enabling task-oriented knowledge organization, autonomous strategy generation, and optimized communication loops. The role of human experts evolves from operators to “intent architect for DIS task framework” and “process quality supervisors,” marking the formation of a new paradigm of human–multi-agent collaboration. Future work will focus on the development and practical deployment of DIS Agent systems.

Key words： DIS Agent; management information systems (MIS); human-multi-agent synergy; S&T documentation and information service (DIS); new paradigm

参考文献

[1] HONG S, ZHENG X, CHEN J, et al. Metagpt: meta programming for multi-agent collaborative framework [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2308.00352.
[2] 刘细文, 付芸, 孙蒙鸽. 驱动情报工作范式变革的情报智能体技术解构[J]. 图书情报工作, 2025, 69(1): 4-15. (LIU X, FU Y, SUN M. Technological deconstruction of DIS Agent driving the paradigm shift in documentation and information service work [J]. Library and information service, 2025, 69(1): 4-15.)
[3] 刘细文, 付芸, 韦华楠. 情报智能体——面向“十五五”的科技情报工作新范式[J]. 农业图书情报学报, 2025, 36(12): 20-34. (LIU X, FU Y, WEI H. DIS Agent: new paradigm of S&T documentation and information service for the fifteenth Five-Year Plan [J]. Journal of library and information science in agriculture, 2024, 36(12): 20-34.)
[4] RUSSELL S J, NORVIG P. Artificial intelligence: a modern approach [M]. Harlow: Pearson, 2016.
[5] ARISTOTLE. Nicomachean ethics [M]. Sydney: Read How You Want, 2006.
[6] KANT I. Foundations of the Metaphysics of Morals [M]. New York: Bobbs-Merrill, 1965.
[7] TURING A M. Computing machinery and intelligence [M]. Dordrecht: Springer, 2009.
[8] WOOLDRIDGE M, JENNINGS N R. Intelligent agents: theory and practice [J]. The knowledge engineering review, 1995, 10(2): 115-152.
[9] SHINN N, CASSANO F, GOPINATH A, et al. Reflexion: language agents with verbal reinforcement learning [C/OL]//Advances in Neural Information Processing Systems 36. New Orleans: NeurIPS, 2023. [2025-05-15]. https://proceedings.neurips.cc/paper_files/paper/2023/file/1b44b878bb782e6954cd888628510e90-Paper-Conference.pdf.
[10] LIU X, YU H, ZHANG H, et al. Agentbench: evaluating llms as agents [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2308.03688.
[11] 陆汝钤, 石纯一, 张松懋, 等. 面向Agent的常识知识库[J]. 中国科学E辑: 技术科学, 2000, 30(5): 453-463. (LU R C, SHI C Y, ZHANG S M, et al. Agent-oriented commonsense knowledge base [J]. Science in china series e: technological sciences, 2000, 30(5): 453-463.)
[12] DENNIS L, FISHER M, LINCOLN N, et al. Practical verification of decision-making in agent-based autonomous systems [J]. Automated software engineering, 2013, 23: 305-359.
[13] CHEN W, SU Y, ZUO J, et al. AgentVerse: facilitating multi-agent collaboration and exploring emergent behaviors [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2308.10848.
[14] GE Y, HUA W, JI J, et al. OpenAGI: when LLM meets domain experts [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2304.04370.
[15] LI G, HAMMOUD H, ITANI H, et al. CAMEL: communicative agents for "mind" exploration of large language model society [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2303.17760.
[16] WANG L, MA C, FENG X, et al. A survey on large language model based autonomous agents[J]. Frontiers of computer science, 2024, 18(6): 186345.
[17] XI Z, CHEN W, 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.
[18] SHORTLIFFE E. Computer-based medical consultations: MYCIN [M]. New York: Elsevier, 2012.
[19] BAKER B, KANITSCHEIDER I, MARKOV T, et al. Emergent tool use from multi-agent autocurricula [J/OL]. [2025-05-15]. arXiv, 2019. https://arxiv.org/abs/1909.07528.
[20] YAO S, ZHAO J, YU D, et al. ReAct: synergizing reasoning and acting in language models [J/OL]. [2025-05-15]. arXiv, 2022. https://arxiv.org/abs/2210.03629.
[21] MORRIS M R, SOHL-DICKSTEIN J N, FIEDEL N, et al. Levels of AGI: operationalizing progress on the path to AGI [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2311.02462.
[22] HUANG Y. Levels of AI agents: from rules to large language models [J/OL]. [2025-05-15]. arXiv, 2024. https://arxiv.org/abs/2405.06643.
[23] SAPKOTA R, ROUMELIOTIS K I, KARKEE M. AI agents vs. agentic AI: a conceptual taxonomy, applications and challenge [J/OL]. [2025-05-15]. arXiv, 2025. https://arxiv.org/html/2505.10468v1.
[24] ACHIAM J, ADLER S, AGARWAL S, et al. Gpt-4 technical report [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2303.08774.
[25] ANIL R, DAI A M, FIRAT O, et al. Palm 2 technical report [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2305.10403.
[26] DURANTE Z, HUANG Q, WAKE N, et al. Agent AI: surveying the horizons of multimodal interaction [J/OL]. [2025-05-15]. arXiv, 2024. https://arxiv.org/abs/2401.03568.
[27] GHALLAB M, NAU D S, TRAVERSO P. Automated planning and acting [M]. Cambridge: Cambridge University Press, 2016.
[28] WANG G, XIE Y, JIANG Y, et al. Voyager: an open-ended embodied agent with large language models [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2305.16291.
[29] ERDOGAN L E, LEE N, KIM S, et al. Plan-and-act: improving planning of agents for long-horizon tasks [J/OL]. [2025-05-15]. arXiv, 2025. https://arxiv.org/abs/2503.09572.
[30] HUANG T, BASU K, ABDELAZIZ I, et al. R2D2: remembering, reflecting and dynamic decision making for web agents [J/OL]. [2025-05-15]. arXiv, 2025. https://arxiv.org/abs/2501.12485.
[31] XIE T, ZHOU F, CHENG Z, et al. Openagents: an open platform for language agents in the wild [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2310.10634.
[32] QIAN C, LIU W, LIU H, et al. Chatdev: communicative agents for software development [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2307.07924.
[33] YANG H, YUE S, HE Y. Auto-gpt for online decision making: Benchmarks and additional opinions [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2306.02224.
[34] WEI J, WANG X, SCHUURMANS D, et al. Chain-of-thought prompting elicits reasoning in large language models [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2201.11903.
[35] STONE P, KAMINKA G, KRAUS S, et al. Ad hoc autonomous agent teams: collaboration without pre-coordination [C]//Proceedings of the AAAI conference on artificial intelligence. Atlanta: AAAI Press, 2010. [2025-05-25]. https://doi.org/10.1609/aaai.v24i1.7529.
[36] JENNINGS N R, SYCARA K, WOOLDRIDGE M. A roadmap of agent research and development [J]. Autonomous agents and multi-agent systems, 1998, 1: 7-38.
[37] MA J, WANG C, RONG L, et al. Exploring multi-agent debate for zero-shot stance detection: a novel approach [J]. Applied sciences, 2025, 15(9): 4612.
[38] LI T, SHI D, JIN S, et al. Multi-agent hierarchical graph attention actor-critic reinforcement learning [J]. Entropy, 2024, 27(4): 1-16.
[39] LI J, YANG F, TOMIZUKA M, et al. Evolvegraph: multi-agent trajectory prediction with dynamic relational reasoning [C/OL]//Advances in Neural Information Processing Systems 33. Ancouver: NeurIPS, 2020. [2025-05-15]. https://proceedings.neurips.cc/paper_files/paper/2020/file/e4d8163c7a068b65a64c89bd745ec360-Paper.pdf
[40] SUMERS T, YAO S, NARASIMHAN K, et al. Cognitive architectures for language agents[J/OL]. [2025-05-15]. arXiv, 2024. https://arxiv.org/abs/2309.02427.
[41] CEMRI M, PAN M Z, YANG S, et al. Why do multi-agent LLM systems fail? [J/OL]. [2025-05-15]. arXiv, 2025. https://arxiv.org/abs/2503.13657.
[42] OPENAI. Introducing deep research [J/OL]. OPENAI, 2025, https://openai.com/index/introducing-deep-research/.
[43] LáLA J, O'DONOGHUE O, SHTEDRITSKI A, et al. Paperqa: retrieval-augmented generative agent for scientific research [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2312.07559.
[44] PINECONE. LangGraph and research agents [J/OL]. [2025-05-15]. 2024, https://www.pinecone.io/learn/langgraph-research-agent/.
[45] SINGH I, BLUKIS V, MOUSAVIAN A, et al. Progprompt: generating situated robot task plans using large language models [J/OL]. [2025-05-15]. arXiv, 2023. https://arxiv.org/abs/2209.11302.
[46] TUFANO M, AGARWAL A, JANG J, et al. AutoDev: automated AI-driven development [J/OL]. [2025-05-15]. arXiv, 2024. https://arxiv.org/abs/2403.08299.
[47] BRAN A M, COX S, SCHILTER O, et al. Augmenting large language models with chemistry tools [J]. Nature machine intelligence, 2024, 6(5): 525-35.
[48] GAO S, FANG A, HUANG Y, et al. Empowering biomedical discovery with AI agents [J]. Cell, 2024, 187(22): 6125-6151.
[49] MA K. AI agents in chemical research: GVIM – an intelligent research assistant system [J]. Digital discovery, 2025, 4: 355-375.
[50] ZHAO X, BLUM M, YANG R, et al. AGENTiGraph: an interactive knowledge graph platform for LLM-based chatbots utilizing private data [J/OL]. [2025-05-15]. arXiv, 2024. https://arxiv.org/abs/2410.11531.
[51] MAJUMDER B P, SURANA H, AGARWAL D, et al. Discoverybench: towards data-driven discovery with large language models [J/OL]. [2025-05-15]. arXiv, 2024. https://arxiv.org/abs/2407.01725.
[52] ZHOU Y, LIU H, SRIVASTAVA T, et al. Hypothesis generation with large language models [J/OL]. [2025-05-15]. arXiv, 2024. https://arxiv.org/abs/2404.04326.
[53] 钱学森. 科技情报工作的科学技术[J]. 情报学刊, 1983, 4. (QIAN X S. The science and technology of scientific & technical information work [J]. Journal of information science, 1983, 4.)
[54] IARPA. FUSE: foresight and understanding from scientific exposition [Z/OL]. IARPA. 2010. [2025-05-25]. https://www.iarpa.gov/research-programs/fuse.
[55] IARPA. SMART: space-based machine automated recognition technique [Z/OL]. IARPA. 2020. [2025-05-25]. https://www.iarpa.gov/research-programs/smart.
[56] NGA. GEOINT Artificial Intelligence [Z/OL]. NGA. 2017. [2025-05-25]. https://www.nga.mil/news/GEOINT_Artificial_Intelligence_.html.
[57] ALEXANDRA C. The future of intelligence analysis: US-Australia project on AI and human machine teaming [R/OL]. 2024. [2025-05-25]. https://www.aspi.org.au/report/the-future-of-intelligence-analysis-us-australia-project-on-ai-and-human-machine-teaming/.
[58] DEE C R. The development of the medical literature analysis and retrieval system (MEDLARS) [J]. Journal of the Medical Library Association, 2007, 95(4): 416-425.
[59] QIU J, QI X, ZHANG T, et al. Alita: generalist agent enabling scalable agentic reasoning with minimal predefinition and maximal self-evolution [J/OL]. [2025-05-15]. arXiv, 2025. https://arxiv.org/abs/2505.20286.
Options
文章导航

/

〈 〉