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。
[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 Infor mation 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,en abling 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.
作者
刘细文
孙蒙鸽
付芸
Liu Xiwen;Sun Mengge;Fu Yun(National Science Library,Chinese Academy of Sciences,Beijing 100190;Department of Information Resources Management,School of Economics and Management,University of ChineseAcademy of Sciences,Beijing 100049)
出处
《图书情报工作》
北大核心
2025年第17期3-15,共13页
Library and Information Service
基金
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。
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
DIS Agent
management information systems(MIS)
human-multi-agent synergy
S&T documentation and information service(DIS)
new paradigm
