OpenClaw对科技文献情报工作的影响与启示

doi:10.13998/j.cnki.issn1002-1248.26-0179

摘要/Abstract

摘要：

[目的/意义] 大语言模型驱动的智能体正从依赖预设流程的任务执行走向面向复杂任务的自主规划与动态执行，科技文献情报工作也随之由阶段式信息处理延伸至连续性情报分析。OpenClaw作为开放式智能体执行框架，具备强大的多消息渠道接入、闭环执行、工具调用、记忆维持与持续运行等智能化能力，其在科技文献情报工作中的应用及可能带来的影响，亟须研究思考。 [方法/过程] 全面梳理分析OpenClaw技术架构体系及核心技术要素，结合科技文献情报工作中的科技文献组织、情报分析流程与知识服务场景，提出未来可能面临的挑战及变化。 [结果/结论] 面向未来“智能科情体系”的快速构建，提出“建立高价值科技情报场景任务清单、通用与专用大模型及特色工具的混合基模模式、一键式自主科学发现与智能情报服务模式、适配智能科情体系场景的国家级文献情报资源语料库建设、垂直领域大模型与智能体协同模式、安全可控的渐进式部署实施路线及全流程闭环治理机制设计”7个方面协同推进建议，期望对行业学科发展有所启示借鉴。

关键词: OpenClaw, 智能体, 科技文献情报, 智能科情体系, 大语言模型

Abstract:

[Purpose/Significance] Agents driven by large language models (LLMs) are transitioning from executing tasks based on predefined workflows to autonomously planning and taking dynamic actions in complex environments. Thus, scientific and technical literature intelligence work is expanding its scope from stage-based information processing to continuous intelligence analysis. OpenClaw is an open agent execution framework that integrates capabilities such as multi-channel access, task orchestration, tool invocation, memory maintenance, and persistent operation. However, a systematic examination of its potential applications, impacts, and practical constraints in the field of scientific and technical literature intelligence remains lacking. This study aims to analyze OpenClaw's technical architecture and comprehensively evaluate how it transforms literature retrieval, knowledge organization, intelligence analysis, and knowledge service processes. [Method/Process] This study systematically reviewed the technical architecture and core components of OpenClaw, focusing on four interdependent layers: the access and communication layer, the agentic loop execution layer, the tool invocation and capability extension layer, and the memory maintenance layer with persistent operation. It related the OpenClaw's architectural logic to the organization of scientific literature, intelligence analysis workflows, and knowledge service scenarios. The study further discussed the changes that OpenClaw's architectural logic may bring to scientific and technical literature intelligence work, including shifts in retrieval patterns, knowledge processing methods, analytical workflows, and service outcomes, as well as the technical and ethical challenges that may emerge in practice. [Results/Conclusions] OpenClaw provides a new technical reference that transitions scientific and technical literature intelligence work from stage-based information processing to continuous knowledge work. Nevertheless, critical challenges persist. These include planning reliability, adaptability of domain knowledge, stability of tool integration, interpretability and traceability, and ethical risks related to data privacy, accountability, and open-ended extension mechanisms. To address these challenges and support the rapid development of an intelligent scientific and technical literature intelligence system, this study proposes the following seven interrelated development directions: 1) establishing task inventories for high-value scientific and technical intelligence scenarios, 2) developing a hybrid foundational model paradigm that combines general-purpose LLMs, task-specific large models, small models, and specialized tool sets, 3) advancing a one-click service model for autonomous scientific discovery and intelligent intelligence support, 4) constructing national-level corpora of literature and intelligence resources tailored to intelligent scientific and technical intelligence scenarios, 5) promoting in-depth collaboration between large, domain-specific models and agents, 6) designing a safe and controllable roadmap for progressive deployment, and 7) establishing a full-process, closed-loop governance mechanism. These proposals are expected to provide valuable references for both disciplinary development and professional practice. They will facilitate the gradual transformation of agents from auxiliary tools into a vital capability for the future of scientific and technical literature intelligence work.

Key words: OpenClaw, intelligent agents, scientific and technical literature intelligence work, intelligent scientific intelligence system, large language models

中图分类号: G350

钱力, 杨颜僖, 张元哲, 胡懋地, 常志军. OpenClaw对科技文献情报工作的影响与启示[J]. 农业图书情报学报, 2026, 38(4): 4-12.

QIAN Li, YANG Yanxi, ZHANG Yuanzhe, HU Maodi, CHANG Zhijun. The Impacts and Implications of OpenClaw for Scientific and Technical Literature Intelligence Work[J]. Journal of library and information science in agriculture, 2026, 38(4): 4-12.

图/表 1

参考文献 24

[1]	Wooldridge M, Jennings N R. Intelligent agents: Theory and practice[J]. The Knowledge Engineering Review, 1995, 10(2): 115-152.
[2]	Plaat A, Van Duijn M, Van Stein N, et al. Agentic large language models, a survey[J]. Journal of Artificial Intelligence Research, 2025, 84: 1-65.
[3]	Wang Lei, Ma Chen, Feng Xueyang, et al. A survey on large language model based autonomous agents[J]. Frontiers of Computer Science, 2024, 18(6): 186345.
[4]	de la Torre-López J, Ramírez A, Romero J R. Artificial intelligence to automate the systematic review of scientific literature[J]. Computing, 2023, 105(10): 2171-2194.
[5]	Scherbakov D, Hubig N, Jansari V, et al. The emergence of large language models as tools in literature reviews: A large language model-assisted systematic review[J]. Journal of the American Medical Informatics Association, 2025, 32(6): 1071-1086.
[6]	宋梦鹏, 白海燕. 基于大语言模型的文献综述智能生成与循证研究[J]. 数据分析与知识发现, 2025, 9(6): 21-34.
	Song Mengpeng, Bai Haiyan. Research on intelligent generation and evidence-based of literature review based on large language model[J]. Data Analysis and Knowledge Discovery, 2025, 9(6): 21-34.
[7]	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, 2024, 36(12): 20-34.
	Liu Xiwen, Fu Yun, Wei Huanan. 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.
[8]	Contributors OpenClaw. OpenClaw: Your own personal AI assistant[EB/OL]. [2026-03-20]. .
[9]	Yao S, Zhao J, Yu D, et al. ReAct: Synergizing reasoning and acting in language models[C]//International Conference on Learning Representations. Addis Ababa: ICLR, 2023.
[10]	Cancedda N, Dessi R, Dwivedi-Yu J, et al. Toolformer: Language models can teach themselves to use tools[C]//Advances in Neural Information Processing Systems 36. Neural Information Processing Systems Foundation, Inc. (NeurIPS), 2023: 68539-68551.
[11]	Packer C, Fang V, Patil S G, et al. MemGPT: Towards LLMs as operating systems[EB/OL]. (2023-10-12)[2026-03-20]. .
[12]	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 Xiwen, Fu Yun, Sun Mengge. 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.
[13]	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.
	Liu Xiwen, Sun Mengge, Fu Yun. From MIS to DIS agent: Reshaping the paradigm of S & T documentation and information service[J]. Library and Information Service, 2025, 69(17): 3-15.
[14]	张智雄, 于改红, 刘熠, 等. ChatGPT对文献情报工作的影响[J]. 数据分析与知识发现, 2023, 7(3): 36-42.
	Zhang Zhixiong, Yu Gaihong, Liu Yi, et al. The influence of ChatGPT on library & information services[J]. Data Analysis and Knowledge Discovery, 2023, 7(3): 36-42.
[15]	李广建, 仵轩, 潘佳立. 从通用AI走向情报AI: 背景、框架及关键技术[J]. 图书情报工作, 2025, 69(20): 3-15.
	Li Guangjian, Wu Xuan, Pan Jiali. From general AI to intelligence AI: Background, framework, and key technologies[J]. Library and Information Service, 2025, 69(20): 3-15.
[16]	Asai A, He J, Shao Rulin, et al. Synthesizing scientific literature with retrieval-augmented language models[J]. Nature, 2026, 650(8103): 857-863.
[17]	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 Yuxiang, Fu Zhenkang, Zeng Pengxiang, 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.
[18]	钱力, 张智雄, 伍大勇, 等. 科技文献大模型: 方法、框架与应用[J]. 中国图书馆学报, 2024, 50(6): 45-58.
	Qian Li, Zhang Zhixiong, Wu Dayong, et al. The large language model for scientific literature: Method, framework, and application[J]. Journal of Library Science in China, 2024, 50(6): 45-58.
[19]	Shan Zhengyang, Xin Jiayun, Zhang Yue, et al. Don’t let the claw grip your hand: A security analysis and defense framework for OpenClaw[PP/OL]. V1. arXiv (2026-03-11)[2026-03-20]. .
[20]	Manik M M H, Wang Ge. OpenClaw agents on moltbook: Risky instruction sharing and norm enforcement in an agent-only social network[PP/OL]. V1. arXiv (2026-02-02)[2026-03-20]. .
[21]	Ying Zonghao, Yang Xiao, Wu Siyang, et al. Uncovering security threats and architecting defenses in autonomous agents: A case study of OpenClaw[PP/OL]. V1. arXiv (2026-03-13)[2026-03-20]. .
[22]	Li F. OpenClaw PRISM: A zero-fork, defense-in-depth runtime security layer for tool-augmented LLM agents[PP/OL]. V1. arXiv (2026-03-12)[2026-03-20]. .
[23]	Liu Songyang, Li Chaozhuo, Wang Chenxu, et al. ClawKeeper: Comprehensive safety protection for OpenClaw agents through skills, plugins, and watchers[PP/OL]. V1. arXiv (2026-03-15)[2026-03-20]. .
[24]	全国人民代表大会. 中华人民共和国国民经济和社会发展第十五个五年规划纲要[EB/OL].(2026-03-16)[2026-03-20]. .