{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T16:10:53Z","timestamp":1792167053525,"version":"4.4.0"},"reference-count":48,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:00:00Z","timestamp":1767830400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Interior and Safety","award":["RS-2023-00241703"],"award-info":[{"award-number":["RS-2023-00241703"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJGI"],"abstract":"<jats:p>Large language models (LLMs) have advanced geospatial artificial intelligence; however, geospatial knowledge-base question answering (GeoKBQA) remains underdeveloped. Prior systems have relied on handcrafted rules and have omitted the splitting of datasets into training, validation, and test sets, thereby hindering fair evaluation. To address these gaps, we propose a prompt-based multi-agent LLM framework (based on GPT-4o) that translates natural-language questions into executable GeoSPARQL. The architecture comprises an intent analyzer, multi-grained retrievers that ground concepts and properties in the OSM tagging schema and map geospatial relations to the GeoSPARQL\/OGC operator inventory, an operator-aware intermediate representation aligned with SPARQL\/GeoSPARQL 1.1, and a query generator. Our approach was evaluated on the GeoKBQA test set using 20 few-shot exemplars per agent. It achieved 85.49 EM (GPT-4o) with less supervision than fine-tuned baselines trained on 3574 instances and substantially outperformed a single-agent GPT-4o prompt. Additionally, we evaluated GPT-4o-mini, which achieved 66.74 EM in a multi-agent configuration versus 47.10 EM with a single agent. The observations showed that the multi-agent gain was higher for the larger model. Our results indicate that, beyond scale, the framework\u2019s structure is important; thus, principled agentic decomposition yields a sample-efficient, execution-faithful path beyond template-centric GeoKBQA under a fair, hold-out evaluation protocol.<\/jats:p>","DOI":"10.3390\/ijgi15010035","type":"journal-article","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T15:33:16Z","timestamp":1767886396000},"page":"35","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Geospatial Knowledge-Base Question Answering Using Multi-Agent Systems"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4827-242X","authenticated-orcid":false,"given":"Jonghyeon","family":"Yang","sequence":"first","affiliation":[{"name":"Social Eco Tech Institute, KonKuk University, Seoul 05029, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3618-4924","authenticated-orcid":false,"given":"Jiyoung","family":"Kim","sequence":"additional","affiliation":[{"name":"Social Eco Tech Institute, KonKuk University, Seoul 05029, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,8]]},"reference":[{"key":"ref_1","unstructured":"Wei, J., Tay, Y., Bommasani, R., Raffel, C., Zoph, B., Borgeaud, S., Yogatama, D., Bosma, M., Zhou, D., and Metzler, D. (2022). Emergent Abilities of Large Language Models. arXiv."},{"key":"ref_2","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_3","first-page":"102936","article-title":"A review of spatially explicit GeoAI applications in urban geography","volume":"112","author":"Liu","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_4","first-page":"103734","article-title":"Mapping the landscape and roadmap of geospatial artificial intelligence (GeoAI) in quantitative human geography: An extensive systematic review","volume":"128","author":"Wang","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_5","unstructured":"Mai, G., Huang, W., Sun, J., Song, S., Mishra, D., Liu, N., Gao, S., Liu, T., Cong, G., and Hu, Y. (2023). On the opportunities and challenges of foundation models for geospatial artificial intelligence. arXiv."},{"key":"ref_6","unstructured":"Tan, C., Cao, Q., Li, Y., Zhang, J., Yang, X., Zhao, H., Wu, Z., Liu, Z., Yang, H., and Wu, N. (2023). On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications. arXiv."},{"key":"ref_7","unstructured":"Manvi, R., Khanna, S., Mai, G., Burke, M., Lobell, D.B., and Ermon, S. (2025, October 01). GeoLLM: Extracting Geospatial Knowledge from Large Language Models. Available online: https:\/\/rohinmanvi.github.io\/GeoLLM\/."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1080\/13658816.2024.2438937","article-title":"GeoTool-GPT: A trainable method for facilitating Large Language Models to master GIS tools","volume":"39","author":"Wei","year":"2025","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_9","first-page":"104312","article-title":"Geospatial large language model trained with a simulated environment for generating tool-use chains autonomously","volume":"136","author":"Zhang","year":"2025","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_10","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_11","unstructured":"Wang, J., Zhao, Z., Wang, Z.J., Da Cheng, B., Nie, L., Luo, W., Yu, Z.Y., and Yuan, L.W. (2025). GeoRAG: A Question-Answering Approach from a Geographical Perspective. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1080\/20964471.2025.2483541","article-title":"Enhancing geodatabases operability: Advanced human-computer interaction through RAG and Multi-Agent Systems","volume":"9","author":"Peng","year":"2025","journal-title":"Big Earth Data"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Feng, Y., Zhang, P., Xiao, G., Ding, L., and Meng, L. (2025). Towards a Barrier-free GeoQA Portal: Natural Language Interaction with Geospatial Data Using Multi-Agent LLMs and Semantic Search. arXiv.","DOI":"10.1016\/j.jag.2025.104825"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Punjani, D., Singh, K., Both, A., Koubarakis, M., Angelidis, I., Bereta, K., Angelidis, I., Bereta, K., Beris, T., and Bilidas, D. (2018, January 6). Template-based question answering over linked geospatial data. Proceedings of the 12th Workshop on Geographic Information Retrieval, Seattle, WA, USA.","DOI":"10.1145\/3281354.3281362"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Hamzei, E., Tomko, M., and Winter, S. (2022, January 25\u201329). Translating place-related questions to GeoSPARQL queries. Proceedings of the ACM Web Conference 2022, Lyon, France.","DOI":"10.1145\/3485447.3511933"},{"key":"ref_16","first-page":"104203","article-title":"The question answering system GeoQA2 and a new benchmark for its evaluation","volume":"134","author":"Kefalidis","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yang, J., Jang, H., and Yu, K. (2023). Geographic Knowledge Base Question Answering over OpenStreetMap. ISPRS Int. J. Geo-Inf., 13.","DOI":"10.3390\/ijgi13010010"},{"key":"ref_18","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, B.Z., Min, S., Iyer, S., Mehdad, Y., and Yih, W.T. (2020, January 16\u201320). Efficient One-Pass End-to-End Entity Linking for Questions. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.","DOI":"10.18653\/v1\/2020.emnlp-main.522"},{"key":"ref_20","unstructured":"Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning (Vol. 1, No. 2), MIT Press."},{"key":"ref_21","unstructured":"Talebirad, Y., and Nadiri, A. (2023). Multi-agent collaboration: Harnessing the power of intelligent LLM agents. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"107200","DOI":"10.1016\/j.neunet.2025.107200","article-title":"Tdag: A multi-agent framework based on dynamic task decomposition and agent generation","volume":"185","author":"Wang","year":"2025","journal-title":"Neural Netw."},{"key":"ref_23","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., Almahairi, A., Babaei, Y., Bashlykov, N., Batra, S., Bhargava, P., and Bhosale, S. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv."},{"key":"ref_24","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F.L., Almeida, D., Altenschmidt, J., Altman, S., and Anadkat, S. (2023). Gpt-4 technical report. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Singh, K., Radhakrishna, A.S., Both, A., Shekarpour, S., Lytra, I., Usbeck, R., Vyas, A., Khikmatullaev, A., Punjani, D., and Lange, C. (2018, January 23\u201327). Why reinvent the wheel: Let\u2019s build question answering systems together. Proceedings of the 2018 World Wide Web Conference, Lyon, France.","DOI":"10.1145\/3178876.3186023"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Finkel, J.R., Grenager, T., and Manning, C.D. (2005, January 25\u201330). Incorporating non-local information into information extraction systems by gibbs sampling. Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL\u201905), Ann Arbor, MI, USA.","DOI":"10.3115\/1219840.1219885"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Usbeck, R., Ngonga Ngomo, A.C., R\u00f6der, M., Gerber, D., Athaide Coelho, S., Auer, S., and Both, A. (2014). AGDISTIS\u2013agnostic disambiguation of named entities using linked open data. ECAI 2014, IOS Press.","DOI":"10.1007\/978-3-319-11964-9_29"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., and Dyer, C. (2016, January 12\u201317). Neural Architectures for Named Entity Recognition. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, CA, USA.","DOI":"10.18653\/v1\/N16-1030"},{"key":"ref_29","unstructured":"Devlin, J., Chang, M.W., Lee, K., and Toutanova, K. (2019, January 2\u20137). Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ferragina, P., and Scaiella, U. (2010, January 26\u201330). Tagme: On-the-fly annotation of short text fragments (by wikipedia entities). Proceedings of the 19th ACM International Conference on Information and Knowledge Management, Toronto, ON, Canada.","DOI":"10.1145\/1871437.1871689"},{"key":"ref_31","first-page":"467","article-title":"Class-based n-gram models of natural language","volume":"18","author":"Brown","year":"1992","journal-title":"Comput. Linguist."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","article-title":"Finding structure in time","volume":"14","author":"Elman","year":"1990","journal-title":"Cogn. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_34","unstructured":"Pascanu, R., Mikolov, T., and Bengio, Y. (2013, January 16\u201321). On the difficulty of training recurrent neural networks. Proceedings of the International Conference on Machine Learning, Atlanta, GA, USA."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_36","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. (2015, January 7\u20139). Neural machine translation by jointly learning to align and translate. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA."},{"key":"ref_37","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_38","unstructured":"Radford, A., Narasimhan, K., Salimans, T., and Sutskever, I. (2018). Improving Language Understanding by Generative Pre-Training, OpenAI. Available online: https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf."},{"key":"ref_39","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref_40","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_41","unstructured":"Kaplan, J., McCandlish, S., Henighan, T., Brown, T.B., Chess, B., Child, R., Gray, S., Radford, A., Wu, J., and Amodei, D. (2020). Scaling laws for neural language models. arXiv."},{"key":"ref_42","unstructured":"Wei, J., Bosma, M., Zhao, V., Guu, K., Yu, A.W., Lester, B., Du, N., Dai, A.M., and Le, Q.V. (2022, January 25\u201329). Finetuned Language Models are Zero-Shot Learners. Proceedings of the International Conference on Learning Representations, Online."},{"key":"ref_43","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Ye, X., Yavuz, S., Hashimoto, K., Zhou, Y., and Xiong, C. (2022, January 22\u201327). RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, Ireland.","DOI":"10.18653\/v1\/2022.acl-long.417"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Shu, Y., Yu, Z., Li, Y., Karlsson, B., Ma, T., Qu, Y., and Lin, C.Y. (2022, January 7\u201311). TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Base. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, Abu Dhabi, United Arab Emirates.","DOI":"10.18653\/v1\/2022.emnlp-main.555"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Wu, L., Petroni, F., Josifoski, M., Riedel, S., and Zettlemoyer, L. (2020, January 16\u201320). Scalable Zero-shot Entity Linking with Dense Entity Retrieval. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), Online.","DOI":"10.18653\/v1\/2020.emnlp-main.519"},{"key":"ref_47","unstructured":"Harris, S., Seaborne, A., and Prud\u2019hommeaux, E. (2025, October 01). SPARQL 1.1 Query Language. W3C Recommendation. Available online: https:\/\/www.w3.org\/TR\/sparql11-query\/."},{"key":"ref_48","unstructured":"Perry, M., Herring, J., and Musen, P. (2025, October 01). GeoSPARQL 1.1: A Geographic Query Language for RDF Data. OGC Implementation Standard. Open Geospatial Consortium. Available online: https:\/\/www.ogc.org\/standards\/geosparql."}],"container-title":["ISPRS International Journal of Geo-Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/1\/35\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T05:17:13Z","timestamp":1768367833000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2220-9964\/15\/1\/35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,8]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["ijgi15010035"],"URL":"https:\/\/doi.org\/10.3390\/ijgi15010035","relation":{},"ISSN":["2220-9964"],"issn-type":[{"value":"2220-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,8]]}}}