{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T12:41:39Z","timestamp":1759495299150,"version":"build-2065373602"},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783662722428","type":"print"},{"value":"9783662722435","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,4]],"date-time":"2025-10-04T00:00:00Z","timestamp":1759536000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-662-72243-5_13","type":"book-chapter","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T12:14:55Z","timestamp":1759493695000},"page":"218-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automating Geospatial Vision Tasks with\u00a0a\u00a0Large Language Model Agent"],"prefix":"10.1007","author":[{"given":"Yuxing","family":"Chen","sequence":"first","affiliation":[]},{"given":"Weijie","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Camille","family":"Kurtz","sequence":"additional","affiliation":[]},{"given":"Sylvain","family":"Lobry","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,10,4]]},"reference":[{"key":"13_CR1","doi-asserted-by":"publisher","unstructured":"Abdin, M., et al.: Phi-3 Technical Report: a highly capable language model locally on your phone. CoRR abs\/2404.14219 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2404.14219","DOI":"10.48550\/ARXIV.2404.14219"},{"key":"13_CR2","doi-asserted-by":"publisher","unstructured":"Bai, J., et al.: Qwen2.5 Technical Report. CoRR abs\/2412.15115 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2412.15115","DOI":"10.48550\/ARXIV.2412.15115"},{"issue":"9","key":"13_CR3","doi-asserted-by":"publisher","first-page":"1477","DOI":"10.3390\/rs16091477","volume":"16","author":"Y Bazi","year":"2024","unstructured":"Bazi, Y., Bashmal, L., Al Rahhal, M.M., Ricci, R., Melgani, F.: Rs-llava: a large vision-language model for joint captioning and question answering in remote sensing imagery. Remote Sens. 16(9), 1477 (2024). https:\/\/doi.org\/10.3390\/rs16091477","journal-title":"Remote Sens."},{"key":"13_CR4","doi-asserted-by":"publisher","unstructured":"Bouzenia, I., Devanbu, P., Pradel, M.: Repairagent: an autonomous, LLM-based agent for program repair. In: 2025 IEEE\/ACM 47th International Conference on Software Engineering (ICSE), pp. 694\u2013694. IEEE Computer Society, Los Alamitos, CA, USA (2025). https:\/\/doi.org\/10.1109\/ICSE55347.2025.00157","DOI":"10.1109\/ICSE55347.2025.00157"},{"key":"13_CR5","doi-asserted-by":"publisher","unstructured":"Dubey, A., et al.: The Llama 3 herd of models. CoRR abs\/2407.21783 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2407.21783","DOI":"10.48550\/ARXIV.2407.21783"},{"key":"13_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/978-3-319-16483-0_54","volume-title":"Bioinformatics and Biomedical Engineering","author":"AF Giraldo-Forero","year":"2015","unstructured":"Giraldo-Forero, A.F., Jaramillo-Garz\u00f3n, J.A., Castellanos-Dom\u00ednguez, C.G.: Evaluation of example-based measures for multi-label classification performance. In: Ortu\u00f1o, F., Rojas, I. (eds.) IWBBIO 2015. LNCS, vol. 9043, pp. 557\u2013564. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16483-0_54"},{"key":"13_CR7","doi-asserted-by":"publisher","unstructured":"Guo, H., Su, X., Wu, C., Du, B., Zhang, L., Li, D.: Remote sensing ChatGPT: solving remote sensing tasks with ChatGPT and visual models. In: IGARSS 2024 - 2024 IEEE International Geoscience and Remote Sensing Symposium, pp. 11474\u201311478. IEEE (2024). https:\/\/doi.org\/10.1109\/IGARSS53475.2024.10640736","DOI":"10.1109\/IGARSS53475.2024.10640736"},{"key":"13_CR8","unstructured":"Guu, K., Lee, K., Tung, Z., Pasupat, P., Chang, M.: Retrieval augmented language model pre-training. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13\u201318 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol. 119, pp. 3929\u20133938. PMLR (2020)"},{"key":"13_CR9","unstructured":"Halter, D.: Jedi: an awesome autocompletion tool for Python (2024). https:\/\/github.com\/davidhalter\/jedi. Accessed: 2024-10-18"},{"key":"13_CR10","doi-asserted-by":"publisher","unstructured":"He, G., Singh, Z., Yoneki, E.: MCTS-GEB: Monte Carlo tree search is a good e-graph builder. In: Proceedings of the 3rd Workshop on Machine Learning and Systems, EuroMLSys 2023, Rome, Italy, 8 May 2023, pp. 26\u201333. ACM (2023). https:\/\/doi.org\/10.1145\/3578356.3592577","DOI":"10.1145\/3578356.3592577"},{"key":"13_CR11","doi-asserted-by":"crossref","unstructured":"Jain, N., Kwiatkowski, R., Ray, B., Ramanathan, M.K., Kumar, V.: On mitigating code LLM hallucinations with API documentation. In: Proceedings of the 47th International Conference on Software Engineering: Software Engineering in Practice (ICSE-SEIP). To appear. IEEE\/ACM (2025)","DOI":"10.1109\/ICSE-SEIP66354.2025.00027"},{"key":"13_CR12","doi-asserted-by":"publisher","unstructured":"Jiang, X., et al.: Self-planning code generation with large language models. ACM Trans. Softw. Eng. Methodol. 33(7) (2024). https:\/\/doi.org\/10.1145\/3672456","DOI":"10.1145\/3672456"},{"key":"13_CR13","doi-asserted-by":"publisher","unstructured":"Kuckreja, K., Danish, M.S., Naseer, M., Das, A., Khan, S., Khan, F.S.: GeoChat: grounded large vision-language model for remote sensing. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27831\u201327840. IEEE Computer Society, Los Alamitos, CA, USA (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02629","DOI":"10.1109\/CVPR52733.2024.02629"},{"issue":"2","key":"13_CR14","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/MGRS.2024.3383473","volume":"12","author":"X Li","year":"2024","unstructured":"Li, X., Wen, C., Hu, Y., Yuan, Z., Zhu, X.X.: Vision-language models in remote sensing: current progress and future trends. IEEE Geosci. Remote Sens. Mag. 12(2), 32\u201366 (2024). https:\/\/doi.org\/10.1109\/MGRS.2024.3383473","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"13_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103497","volume":"124","author":"X Li","year":"2023","unstructured":"Li, X., Wen, C., Hu, Y., Zhou, N.: Rs-clip: zero shot remote sensing scene classification via contrastive vision-language supervision. Int. J. Appl. Earth Obs. Geoinf. 124, 103497 (2023). https:\/\/doi.org\/10.1016\/j.jag.2023.103497","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"13_CR16","doi-asserted-by":"publisher","unstructured":"Li, Z., Ning, H.: Autonomous GIS: the next-generation AI-powered GIS. Int. J. Digit. Earth 16(2), 4668\u20134686 (2023). https:\/\/doi.org\/10.1080\/17538947.2023.2278895","DOI":"10.1080\/17538947.2023.2278895"},{"key":"13_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2024.3425815","volume":"62","author":"C Liu","year":"2024","unstructured":"Liu, C., Chen, K., Zhang, H., Qi, Z., Zou, Z., Shi, Z.: Change-agent: toward interactive comprehensive remote sensing change interpretation and analysis. IEEE Trans. Geosci. Remote Sens. 62, 1\u201316 (2024). https:\/\/doi.org\/10.1109\/TGRS.2024.3425815","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"13_CR18","doi-asserted-by":"publisher","unstructured":"Liu, F., et al.: Exploring and evaluating hallucinations in LLM-powered code generation. CoRR abs\/2404.00971 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2404.00971","DOI":"10.48550\/ARXIV.2404.00971"},{"key":"13_CR19","doi-asserted-by":"publisher","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26286\u201326296 (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.02484","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"13_CR20","doi-asserted-by":"publisher","unstructured":"Liu, J., Chen, Y., Liu, M., Peng, X., Lou, Y.: STALL+: Boosting LLM-based repository-level code completion with static analysis. CoRR abs\/2406.10018 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2406.10018","DOI":"10.48550\/ARXIV.2406.10018"},{"key":"13_CR21","doi-asserted-by":"publisher","unstructured":"Schick, T., et al.: Toolformer: Language models can teach themselves to use tools. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NeurIPS). Curran Associates Inc., Red Hook, NY, USA (2023). https:\/\/doi.org\/10.5555\/3666122.3669119","DOI":"10.5555\/3666122.3669119"},{"key":"13_CR22","doi-asserted-by":"publisher","unstructured":"Singh, S., Fore, M., Stamoulis, D.: GeoLLM-Engine: a realistic environment for building geospatial copilots. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 585\u2013594 (2024). https:\/\/doi.org\/10.1109\/CVPRW63382.2024.00063","DOI":"10.1109\/CVPRW63382.2024.00063"},{"key":"13_CR23","doi-asserted-by":"publisher","unstructured":"Team, C.: CodeGemma: Open code models based on Gemma. CoRR abs\/2406.11409 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2406.11409","DOI":"10.48550\/ARXIV.2406.11409"},{"key":"13_CR24","doi-asserted-by":"publisher","unstructured":"Wang, X., Chen, Y., Yuan, L., Zhang, Y., Li, Y., Peng, H., Ji, H.: Executable code actions elicit better LLM agents. In: Salakhutdinov, R., et al., (eds.) Proceedings of the 41st International Conference on Machine Learning (ICML 2024), Proceedings of Machine Learning Research, vol.\u00a0235, pp. 50208\u201350232. PMLR (2024). https:\/\/doi.org\/10.5555\/3692070.3694124","DOI":"10.5555\/3692070.3694124"},{"key":"13_CR25","doi-asserted-by":"publisher","first-page":"17007","DOI":"10.1109\/JSTARS.2024.3438376","volume":"17","author":"J Wu","year":"2024","unstructured":"Wu, J., Gan, W., Chao, H.C., Philip, S.Y.: Geospatial big data: survey and challenges. IEEE J.Sel. Top. Appl. Earth Obser. Remote Sens. 17, 17007\u201317020 (2024). https:\/\/doi.org\/10.1109\/JSTARS.2024.3438376","journal-title":"IEEE J.Sel. Top. Appl. Earth Obser. Remote Sens."},{"key":"13_CR26","doi-asserted-by":"publisher","unstructured":"Yang, A., et al.: Qwen2 Technical Report. CoRR abs\/2407.10671 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2407.10671","DOI":"10.48550\/ARXIV.2407.10671"},{"key":"13_CR27","unstructured":"Yao, S., et al.: ReAct: synergizing reasoning and acting in language models. In: International Conference on Learning Representations (ICLR 2023). OpenReview.net, Kigali, Rwanda (2023)"},{"key":"13_CR28","doi-asserted-by":"publisher","unstructured":"Zhan, Y., Xiong, Z., Yuan, Y.: SkyEyeGPT: unifying remote sensing vision-language tasks via instruction tuning with large language model. CoRR abs\/2401.09712 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2401.09712","DOI":"10.48550\/ARXIV.2401.09712"},{"key":"13_CR29","doi-asserted-by":"publisher","unstructured":"Zhang, K., Li, J., Li, G., Shi, X., Jin, Z.: CodeAgent: enhancing code generation with tool-integrated agent systems for real-world repo-level coding challenges. In: Ku, L.W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 13643\u201313658. Association for Computational Linguistics, Bangkok (2024). https:\/\/doi.org\/10.18653\/v1\/2024.acl-long.737","DOI":"10.18653\/v1\/2024.acl-long.737"},{"key":"13_CR30","doi-asserted-by":"publisher","unstructured":"Zhang, S., et al.: CIBench: evaluating your LLMs with a code interpreter plugin. CoRR abs\/2407.10499 (2024). https:\/\/doi.org\/10.48550\/ARXIV.2407.10499","DOI":"10.48550\/ARXIV.2407.10499"},{"key":"13_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103976","volume":"131","author":"Y Zhang","year":"2024","unstructured":"Zhang, Y., Wei, C., He, Z., Yu, W.: Geogpt: an assistant for understanding and processing geospatial tasks. Int. J. Appl. Earth Obs. Geoinf. 131, 103976 (2024). https:\/\/doi.org\/10.1016\/j.jag.2024.103976","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"13_CR32","unstructured":"Zhuo, T.Y., et al.: BigCodeBench: benchmarking code generation with diverse function calls and complex instructions. (2025)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track and Applied Data Science Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-662-72243-5_13","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T12:15:03Z","timestamp":1759493703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-662-72243-5_13"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,4]]},"ISBN":["9783662722428","9783662722435"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-662-72243-5_13","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,4]]},"assertion":[{"value":"4 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Porto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecmlpkdd.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}