地理空间多智能体协同:架构、技术及应用
Geospatial Multi-Agent Collaboration: Architecture, Technologies, and Applications
地理空间多智能体协同是以地理空间大模型为核心,通过多智能体相互协作、自组织、自学习、自适应,持续优化迭代,形成协同的智能新模式。本文在梳理地理空间多智能体协同发展现状的基础上,分析了其内涵与特征,提出了地理空间多智能体协同的体系架构及协同模式,涵盖“物理感知 ‒ 数据治理 ‒ 智能引擎 ‒ 多智能体 ‒ 业务应用”五层框架以及水平协同、垂直协同、混合协同3种协同模式,总结了多模态数据感知与表征、地理知识深度融合与理解、专业工具智能调用与质量控制、多智能体协同调度与自我优化等关键技术,开展了灾害应急保障服务场景示范应用。本研究旨在为构建具备任务自规划、工具自调用、结果自评估与记忆自进化能力的智能系统奠定基础,推动地理空间智能应用从静态分析向动态智能响应演进,为自然资源监测、应急管理、智慧城市等提供新一代决策支持。
Geospatial multi-agent collaboration is a new intelligent collaborative paradigm centered around geospatial large models, where multiple agents collaborate, self-organize, self-learn, and self-adapt through continuous optimization and iteration. Based on an analysis of the current development status of geospatial multi-agent collaboration, this study explores its essence and characteristics. It also presents a five-layer system architecture that comprises physical perception, data governance, intelligent engine, multi-agent, and business application layers, as well as three collaboration modes: horizontal, vertical, and hybrid collaboration. Moreover, the study summarizes key technologies such as multimodal data perception and representation, deep integration and understanding of geographical knowledge, intelligent utilization of specialized tools and quality control, as well as collaborative scheduling and self-optimization of multiple agents. Demonstration applications for disaster emergency support service scenarios are also carried out. This study aims to lay a foundation for constructing intelligent systems with capabilities such as task self-planning, tool self-invocation, result self-evaluation, and memory self-evolution. This will advance geospatial applications from static analysis to dynamic intelligent response, providing next-generation decision support for fields such as natural resource monitoring, emergency management, and smart cities.
| [1] |
陈军,艾廷华,闫利, 智能化测绘的混合计算范式与方法研究[J]. 测绘学报,2024,53(6):985-998. |
| [2] |
Chen J,Ai T H,Yan L,et al. Hybrid computational paradigm and methods for intelligentized surveying and mapping[J]. Acta Geodaetica et Cartographica Sinica,2024,53(6):985-998. |
| [3] |
Derouiche H,Brahmi Z,Mazeni H. Agentic AI frameworks:Architectures,protocols,and design challenges[PP/OL]. arXiv (2025-08-13)[2026-01-28]. https://doi.org/10.48550/arXiv.2508.10146. |
| [4] |
Xu W,Yu Z,Mu B,et al. RS-Agent:Automating remote sensing tasks through intelligent agent[J]. Science China Information Sciences,2026,69(8):180302. |
| [5] |
李圆,祝华夏,付媛媛, AI智能体驱动产业变革研究报告[R]. 北京:中国软件行业协会信息主管(CIO)分会,2025:3. |
| [6] |
Li Y,Zhu H X,Fu Y Y,et al. Research report on industrial transformation driven by AI intelligent agents[R]. Beijing:China Software Industry Association Information Chief (CIO) Branch,2025:3. |
| [7] |
Abou Ali M,Dornaika F,Charafeddine J. Agentic AI:A comprehensive survey of architectures,applications,and future directions[J]. Artificial Intelligence Review,2025,59(1):11. |
| [8] |
Bell A,Aides A,Helmy A,et al. Earth AI:Unlocking geospatial insights with foundation models and cross-modal reasoning[PP/OL]. V4. arXiv(2026-02-18)[2026-03-28]. https://doi.org/10.48550/arXiv.2510.18318. |
| [9] |
Zhang X Q,Dong X F,Wang Y R,et al. A survey of multi-AI agent collaboration:Theories,technologies and applications[C]//The 2nd Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence,2025:1875-1881. |
| [10] |
Wang Y T,Pan Y H,Su Z,et al. Large model-based agents:State-of-the-art,cooperation paradigms,security and privacy,and future trends[J]. IEEE Communications Surveys & Tutorials,2026,28:1906-1949. |
| [11] |
Talebirad Y,Nadiri A. Multi-agent collaboration:Harnessing the power of intelligent LLM agents[PP/OL]. arXiv (2023-06-05)[2026-01-28]. https://doi.org/10.48550/arXiv.2306.03314. |
| [12] |
Wu Q Y,Bansal G,Zhang J Y,et al. AutoGen:Enabling next-gen LLM applications via multi-agent conversations[C]//The First Conference on Language Modeling (COLM),2024:1328. |
| [13] |
Fourney A,Bansal G,Mozannar H,et al. Magentic-one:A generalist multi-agent system for solving complex tasks[PP/OL]. arXiv (2024-11-07)[2026-01-28]. https://doi.org/10.48550/arXiv.2411.04468. |
| [14] |
Wang J L,Duan Z H. Agent AI with LangGraph:A modular framework for enhancing machine translation using large language models[PP/OL]. arXiv(2024-12-05)[2026-01-28]. https://doi.org/10.48550/arXiv.2412.03801. |
| [15] |
Duan Z H,Wang J L. Exploration of LLM multi-agent application implementation based on LangGraph+CrewAI[PP/OL]. arXiv (2024-11-27)[2026-01-28]. https://doi.org/10.48550/arXiv.2411.18241. |
| [16] |
Roumeliotis K I,Tselikas N D. ChatGPT and open-AI models:A preliminary review[J]. Future Internet,2023,15(6):192. |
| [17] |
Sun Z H,Sandoval L,Crystal-Ornelas R,et al. A review of earth artificial intelligence[J]. Computers & Geosciences,2022,159:105034. |
| [18] |
江文源,朱剑,马骁驰, 信创背景下中国GIS软件的发展研究与实践[J]. 科技与创新,2025(23):221-223. |
| [19] |
Jiang W Y,Zhu J,Ma X C,et al. Research and practice on the development of GIS software in China under the background of Information Innovation[J]. Science and Technology & Innovation,2025(23):221-223. |
| [20] |
Zhang J F,Hua X S,Huang J Q,et al. City brain:Practice of large-scale artificial intelligence in the real world[J]. IET Smart Cities,2019,1(1):28-37. |
| [21] |
Lee C,Paramanayakam V,Karatzas A,et al. Multi-agent geospatial copilots for remote sensing workflows[PP/OL]. arXiv (2025-01-27)[2026-01-28]. https://doi.org/10.48550/arXiv.2501.16254. |
| [22] |
Park J S,O’Brien J,Cai C J,et al. Generative agents:Interactive simulacra of human behavior[C]//The 36th Annual ACM Symposium on User Interface Software and Technology,2023:1-22. |
| [23] |
Kuckreja K,Danish M S,Naseer M,et al. GeoChat:Grounded large vision-language model for remote sensing[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2024. |
| [24] |
Guo Z J,Wang J,Ling F H,et al. A self-evolving AI agent system for climate science[PP/OL]. V3. arXiv(2025-11-03)[2026-01-28]. https://doi.org/10.48550/arXiv.2507.17311. |
| [25] |
Tsokanaridou M,Hackstein J H,Hoxha G,et al. DA4DTE:An agentic system for enhancing the accessibility of digital twins of earth[C]//The Workshop on AI-driven Data Engineering and Reusability for Earth and Space Sciences (DARES’25) Co-located with the 28th European conference on artificial intelligence (ECAI 2025),2025. |
| [26] |
Lin Q M,Hu R,Li H X,et al. ShapefileGPT:A multi-agent large language model framework for automated shapefile processing[J]. International Journal of Digital Earth,2025,18(2):2577884. |
| [27] |
Liu Z R,Zhao D P,Yuan B,et al. RescueADI:Adaptive disaster interpretation in remote sensing images with autonomous agents[J]. IEEE Transactions on Geoscience and Remote Sensing,2025,63:5611814. |
| [28] |
Yang K,Yang D K,Zhang J Y,et al. Spatio-temporal domain awareness for multi-agent collaborative perception[C]//2023 IEEE/CVF International Conference on Computer Vision (ICCV),2023:23326-23335. |
| [29] |
Hong S R,Zhuge M C,Chen J,et al. MetaGPT:Meta programming for a multi-agent collaborative framework[C]//The Twelfth International Conference on Learning Representations (ICLR 2024),2024:23247-23275. |
| [30] |
Wang L,Ma C,Feng X Y,et al. A survey on large language model based autonomous agents[J]. Frontiers of Computer Science,2024,18(6):186345. |
| [31] |
Amirkhani A,Barshooi A H. Consensus in multi-agent systems:A review[J]. Artificial Intelligence Review,2022,55(5):3897-3935. |
| [32] |
董学辉,李凡,王帅, 多源地理空间数据服务标准化融合技术[J]. 测绘与空间地理信息,2025,48(11):125-127,131. |
| [33] |
Dong X H,Li F,Wang S,et al. Standardization fusion technology of multi-source geospatial data service[J]. Geomatics & Spatial Information Technology,2025,48(11):125-127,131. |
| [34] |
陈军,张姗琪,张兵, 时空信息赋能国土空间规划的发展方向[J]. 城市规划学刊,2025(2):20-27. |
| [35] |
Chen J,Zhang S Q,Zhang B,et al. Development pathways of spatiotemporal information-empowered territorial spatial planning[J]. Urban Planning Forum,2025(2):20-27. |
| [36] |
张良培,何江,杨倩倩, 数据驱动的多源遥感信息融合研究进展[J]. 测绘学报,2022,51(7):1317-1337. |
| [37] |
Zhang L P,He J,Yang Q Q,et al. Data-driven multi-source remote sensing data fusion:Progress and challenges[J]. Acta Geodaetica et Cartographica Sinica,2022,51(7):1317-1337. |
| [38] |
Lei Z,Lei T L. Towards topological geospatial conflation:An optimized node-arc conflation model for road networks[J]. ISPRS International Journal of Geo-Information,2024,13(1):15. |
| [39] |
于鲁平. 生态保护红线法律制度建设时空主要矛盾解析[J]. 政法论丛,2019(6):138-148. |
| [40] |
Yu L P. Analysis on the main contradiction in the construction of the legal system of ecological protection red line[J]. Journal of Political Science and Law,2019(6):138-148. |
| [41] |
周新民,胡宜桂,刘文洁, 基于多模态多层级数据融合方法的城市功能识别研究[J]. 计算机科学,2021,48(9):50-58. |
| [42] |
Zhou X M,Hu Y G,Liu W J,et al. Research on urban function recognition based on multi-modaland multi-level data fusion methods[J]. Computer Science,2021,48(9):50-58. |
| [43] |
许斐. 基于5G网络的超高清动态视频实时编码与低延时传输技术研究[J]. 数字化传播,2024(8):75-77. |
| [44] |
Xu F. Research on real-time encoding and low-latency transmission technology for ultra-high-definition dynamic video based on 5G networks[J]. Digital Communication,2024(8):75-77. |
| [45] |
万冉冉,梁珍宝,杨莹华. 国土空间多模态语义对齐:时空权重与消解机制研究[J/OL]. 地理空间信息,2025-12-16. https://link.cnki.net/urlid/42.1692.P.20251215.1732.004. |
| [46] |
Wan R R,Liang Z B,Yang Y H. Multi-modal semantic alignment of national space:Research on spatial-temporal weight and resolution mechanism[J/OL]. China Industrial Economics,2025-12-16. https://link.cnki.net/urlid/42.1692.P.20251215.1732.004. |
| [47] |
高超,杨莹,陈世超, 多模态模型驱动的具身智能研究综述[J]. 智能感知工程,2025,2(2):1-12. |
| [48] |
Gao C,Yang Y,Chen S C,et al. Survey on multimodal model-driven embodied intelligence research[J]. Intelligent Perception Engineering,2025,2(2):1-12. |
| [49] |
Jin W Q,Du H Y,Tang S X,et al. A comprehensive survey on multi-agent cooperative decision-making:Scenarios,approaches,challenges and perspectives[PP/OL]. V2. arXiv(2025-03-17)[2026-01-28]. https://doi.org/10.48550/arXiv.2503.13415. |
| [50] |
熊骏,张文博,熊智, 多智能体协同路径规划综述[J]. 系统仿真学报,2025,37(12):3033-3049. |
| [51] |
Xiong J,Zhang W B,Xiong Z,et al. Survey of cooperative multi-agent path finding[J]. Journal of System Simulation,2025,37(12):3033-3049. |
| [52] |
Dong Q,Wu Z Y,Lu J,et al. Existence and practice of gaming:Thoughts on the development of multi-agent system gaming[J]. Frontiers of Information Technology & Electronic Engineering,2022,23(7):995-1001. |
| [53] |
Rabinovich E,Ackerman S,Raz O,et al. Predicting question-answering performance of large language models through semantic consistency[C]//The Third Workshop on Natural Language Generation,Evaluation,and Metrics (GEM),2023:138-154. |
| [54] |
徐东伟,杨涵凯,顾同成, 大语言模型驱动的匝道合并多智能体认知协同安全决策框架[J/OL]. 交通运输工程学报,2025-12-12. https://doi.org/10.19818/j.cnki.1671-1637.2026.113. |
| [55] |
Xu D W,Yang H K,Gu T C,et al. Large language model driven multi-agent cognitive collaborative security decision framework for ramp merge[J/OL]. China Industrial Economics,2025-12-12. https://doi.org/10.19818/j.cnki.1671-1637.2026.113. |
| [56] |
Xu Y C,Chen L L,Lu Z H,et al. An adaptive mechanism for dynamically collaborative computing power and task scheduling in edge environment[J]. IEEE Internet of Things Journal,2023,10(4):3118-3129. |
| [57] |
Guo Y K,Zhu J,Wu J L,et al. An automated construction method of 3D knowledge graph based on multi-agent systems in virtual geographic scene[J]. International Journal of Digital Earth,2025,18(1):2449185. |
| [58] |
李琳慧,王宇,刘越岩, 特征相似度驱动的不动产多源异构数据快速融合模型[J]. 武汉大学学报(信息科学版),2025,50(7):1447-1454. |
| [59] |
Li L H,Wang Y,Liu Y Y,et al. A fast fusion model for multi-source heterogeneous real estate data driven by feature similarity[J]. Geomatics and Information Science of Wuhan University,2025,50(7):1447-1454. |
| [60] |
于瀚洋,蓝朝桢,王龙号, 多模态遥感影像匹配的深度学习研究进展与趋势[J]. 地球信息科学学报,2025,27(8):1896-1919. |
| [61] |
Yu H Y,Lan C Z,Wang L H,et al. Research advances and development trends of deep learning methods for multimodal remote sensing image matching[J]. Journal of Geo-Information Science,2025,27(8):1896-1919. |
| [62] |
向俞明,白植达,陈锦杨, 众源数据辅助的高分辨率SAR影像控制点自动提取与校正方法研究[J]. 雷达学报(中英文),2026,15(2):710-726. |
| [63] |
Xiang Y M,Bai Z D,Chen J Y,et al. Research on automatic control point extraction and correction method for high-resolution synthetic aperture radar imagery assisted by multi-source data[J]. Journal of Radars,2026,15(2):710-726. |
| [64] |
Yaqoob A,Bi T,Muntean G M. A survey on adaptive 360° video streaming:Solutions,challenges and opportunities[J]. IEEE Communications Surveys & Tutorials,2020,22(4):2801-2838. |
| [65] |
张继贤,顾海燕,杨懿, 高分辨率遥感影像智能解译研究进展与趋势[J]. 遥感学报,2021,25(11):2198-2210. |
| [66] |
Zhang J X,Gu H Y,Yang Y,et al. Research progress and trend of high-resolution remote sensing imagery intelligent interpretation[J]. Journal of Remote Sensing,2021,25(11):2198-2210. |
| [67] |
马丽莎,刘殿锋,刘耀林. 城市扩张与生态空间非线性动态耦合关系梯度分析模型[J]. 地球信息科学学报,2023,25(10):1968-1985. |
| [68] |
Ma L S,Liu D F,Liu Y L. Modelling gradient changes of non-linear dynamic coupling relationships between urban expansion and ecological land[J]. Journal of Geo-Information Science,2023,25(10):1968-1985. |
| [69] |
Attouche L,Baazizi M A,Colazzo D,et al. Validation of modern JSON schema:Formalization and complexity[J]. Proceedings of the ACM on Programming Languages,2024,8(POPL):1451-1481. |
| [70] |
刘海天,郭烨,石剑涛, 分布式优化在互联电网中的应用分析及展望[J]. 电力系统自动化,2024,48(22):22-42. |
| [71] |
Liu H T,Guo Y,Shi J T,et al. Application analysis and prospect of distributed optimization in interconnected power grid[J]. Automation of Electric Power Systems,2024,48(22):22-42. |
| [72] |
Pappula K K,Anasuri S,Rusum G P. Building observability into full-stack systems:Metrics that matter[J]. International Journal of Emerging Research in Engineering and Technology,2021,2:48-58. |
| [73] |
Chen Y,Ding Y M,Hu Z Z,et al. Geometrized task scheduling and adaptive resource allocation for large-scale edge computing in smart cities[J]. IEEE Internet of Things Journal,2025,12(10):14398-14419. |
中国工程院咨询项目“面向2040的实景三维中国发展战略与推进路径研究”(L2424236)
Funding project: Chinese Academy of Engineering project "Research on the Practical, Three-Dimensional Development Strategy for China by 2040 and Its Implementation Path"(L2424236)
/
| 〈 |
|
〉 |