{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T15:57:08Z","timestamp":1781884628887,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":65,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,22]]},"DOI":"10.1145\/3715335.3735494","type":"proceedings-article","created":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T09:31:52Z","timestamp":1752831112000},"page":"608-619","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Geo-OLM: Enabling Sustainable Earth Observation Studies with Cost-Efficient Open Language Models & State-Driven Workflows"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1682-9350","authenticated-orcid":false,"given":"Dimitrios","family":"Stamoulis","sequence":"first","affiliation":[{"name":"Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5734-4221","authenticated-orcid":false,"given":"Diana","family":"Marculescu","sequence":"additional","affiliation":[{"name":"Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,21]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Marah Abdin Jyoti Aneja Harkirat Behl S\u00e9bastien Bubeck Ronen Eldan Suriya Gunasekar Michael Harrison Russell\u00a0J Hewett Mojan Javaheripi Piero Kauffmann et\u00a0al. 2024. Phi-4 technical report. arXiv preprint arXiv:2412.08905 (2024)."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3678717.3691221"},{"key":"e_1_3_3_1_4_2","unstructured":"Nikolaos\u00a0Ioannis Bountos Arthur Ouaknine and David Rolnick. 2023. FoMo-Bench: a multi-modal multi-scale and multi-task Forest Monitoring Benchmark for remote sensing foundation models. arXiv preprint arXiv:2312.10114 (2023)."},{"key":"e_1_3_3_1_5_2","unstructured":"Yuxing Chen Weijie Wang Sylvain Lobry and Camille Kurtz. 2024. An llm agent for automatic geospatial data analysis. arXiv preprint arXiv:2410.18792 (2024)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.2760\/098587"},{"key":"e_1_3_3_1_7_2","unstructured":"Microsoft Corp.2025. Global ML Building Footprints. https:\/\/github.com\/microsoft\/GlobalMLBuildingFootprints Accessed: 2025-01-30."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3678717.3691292"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-demo.8"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","unstructured":"K. Didan. 2015. MOD13A3 MODIS\/Terra Vegetation Indices Monthly L3 Global 1km SIN Grid V006. 10.5067\/MODIS\/MOD13A3.006 Accessed 2025-01-07.","DOI":"10.5067\/MODIS\/MOD13A3.006"},{"key":"e_1_3_3_1_11_2","unstructured":"Azure Documentation. 2024. What is Azure Machine Learning prompt flow?https:\/\/learn.microsoft.com\/en-us\/azure\/machine-learning\/prompt-flow\/overview-what-is-prompt-flow?view=azureml-api-2 Accessed: 2025-01-30."},{"key":"e_1_3_3_1_12_2","series-title":"Proceedings of Machine Learning Research","first-page":"11642","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Drouin Alexandre","year":"2024","unstructured":"Alexandre Drouin, Maxime Gasse, Massimo Caccia, Issam\u00a0H. Laradji, Manuel Del\u00a0Verme, Tom Marty, David Vazquez, Nicolas Chapados, and Alexandre Lacoste. 2024. WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?. In Proceedings of the 41st International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0235). PMLR, 11642\u201311662. https:\/\/proceedings.mlr.press\/v235\/drouin24a.html"},{"key":"e_1_3_3_1_13_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et\u00a0al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_3_1_14_2","unstructured":"Earth Science Data and Information System (ESDIS). 2025. NASA Earthdata Search. https:\/\/search.earthdata.nasa.gov. Accessed 2025-01-07."},{"key":"e_1_3_3_1_15_2","unstructured":"Adam Fourney Gagan Bansal Hussein Mozannar Cheng Tan Eduardo Salinas Friederike Niedtner Grace Proebsting Griffin Bassman Jack Gerrits Jacob Alber et\u00a0al. 2024. Magentic-one: A generalist multi-agent system for solving complex tasks. arXiv preprint arXiv:2411.04468 (2024)."},{"key":"e_1_3_3_1_16_2","unstructured":"Global Fishing Watch. 2025. Global Fishing Watch. https:\/\/globalfishingwatch.org\/. Accessed 2025-01-30."},{"key":"e_1_3_3_1_17_2","unstructured":"Vinicius\u00a0G Goecks and Nicholas\u00a0R Waytowich. 2023. Disasterresponsegpt: Large language models for accelerated plan of action development in disaster response scenarios. arXiv preprint arXiv:2306.17271 (2023)."},{"key":"e_1_3_3_1_18_2","unstructured":"Daya Guo Dejian Yang Haowei Zhang Junxiao Song Ruoyu Zhang Runxin Xu Qihao Zhu Shirong Ma Peiyi Wang Xiao Bi et\u00a0al. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948 (2025)."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Matthew\u00a0C Hansen Peter\u00a0V Potapov Rebecca Moore Matt Hancher Svetlana\u00a0A Turubanova Alexandra Tyukavina David Thau Stephen\u00a0V Stehman Scott\u00a0J Goetz Thomas\u00a0R Loveland et\u00a0al. 2013. High-resolution global maps of 21st-century forest cover change. science 342 6160 (2013) 850\u2013853.","DOI":"10.1126\/science.1244693"},{"key":"e_1_3_3_1_20_2","unstructured":"Qitian\u00a0Jason Hu Jacob Bieker Xiuyu Li Nan Jiang Benjamin Keigwin Gaurav Ranganath Kurt Keutzer and Shriyash\u00a0Kaustubh Upadhyay. 2024. ROUTERBENCH: A Benchmark for Multi-LLM Routing System. arXiv preprint arXiv:2403.12031 (2024)."},{"key":"e_1_3_3_1_21_2","unstructured":"Yuan Hu Jianlong Yuan Congcong Wen Xiaonan Lu and Xiang Li. 2023. Rsgpt: A remote sensing vision language model and benchmark. arXiv preprint arXiv:2307.15266 (2023)."},{"key":"e_1_3_3_1_22_2","unstructured":"Yanan Jian Fuxun Yu Simranjit Singh and Dimitrios Stamoulis. 2023. Stable diffusion for aerial object detection. arXiv preprint arXiv:2311.12345 (2023)."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_3_1_25_2","unstructured":"Alexandre Lacoste Nils Lehmann Pau Rodriguez Evan Sherwin Hannah Kerner Bj\u00f6rn L\u00fctjens Jeremy Irvin David Dao Hamed Alemohammad Alexandre Drouin et\u00a0al. 2024. Geo-bench: Toward foundation models for earth monitoring. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_26_2","unstructured":"LangChain. 2024. LangChain Documentation. https:\/\/python.langchain.com\/docs\/introduction\/ Accessed: 2025-01-30."},{"key":"e_1_3_3_1_27_2","unstructured":"Chaehong Lee Varatheepan Paramanayakam Andreas Karatzas Yanan Jian Michael Fore Heming Liao Fuxun Yu Ruopu Li Iraklis Anagnostopoulos and Dimitrios Stamoulis. 2025. Multi-Agent Geospatial Copilots for Remote Sensing Workflows. arxiv:2501.16254"},{"key":"e_1_3_3_1_28_2","unstructured":"Jiajia Li Kyle Lammers Xunyuan Yin Xiang Yin Long He Renfu Lu and Zhaojian Li. 2024. MetaFruit Meets Foundation Models: Leveraging a Comprehensive Multi-Fruit Dataset for Advancing Agricultural Foundation Models. arXiv preprint arXiv:2407.04711 (2024)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Fan Liu Delong Chen Zhangqingyun Guan Xiaocong Zhou Jiale Zhu Qiaolin Ye Liyong Fu and Jun Zhou. 2024. RemoteCLIP: A Vision Language Foundation Model for Remote Sensing. IEEE Transactions on Geoscience and Remote Sensing 62 (2024) 1\u201316.","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"e_1_3_3_1_30_2","unstructured":"Yanming Liu Xinyue Peng Yuwei Zhang Jiannan Cao Xuhong Zhang Sheng Cheng Xun Wang Jianwei Yin and Tianyu Du. 2024. Tool-Planner: Dynamic Solution Tree Planning for Large Language Model with Tool Clustering. arXiv preprint arXiv:2406.03807 (2024)."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","unstructured":"Simon Lobentanzer Shuhan Feng Nicole Bruderer et\u00a0al. 2025. A platform for the biomedical application of large language models. Nature Biotechnology (2025). 10.1038\/s41587-024-02534-3","DOI":"10.1038\/s41587-024-02534-3"},{"key":"e_1_3_3_1_32_2","unstructured":"Pan Lu Baolin Peng Hao Cheng Michel Galley Kai-Wei Chang Ying\u00a0Nian Wu Song-Chun Zhu and Jianfeng Gao. 2024. Chameleon: Plug-and-play compositional reasoning with large language models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","unstructured":"Alexei Lyapustin and Yujie Wang. 2018. MCD19A2 MODIS\/Terra+Aqua Land Aerosol Optical Depth Daily L2G Global 1km SIN Grid V006. 10.5067\/MODIS\/MCD19A2.006. Accessed 2025-01-07.","DOI":"10.5067\/MODIS\/MCD19A2.006"},{"key":"e_1_3_3_1_34_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Mall Utkarsh","year":"2024","unstructured":"Utkarsh Mall, Cheng\u00a0Perng Phoo, Meilin\u00a0Kelsey Liu, Carl Vondrick, Bharath Hariharan, and Kavita Bala. 2024. Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_1_35_2","unstructured":"Microsoft Azure. 2025. Azure Virtual Machines \u2013 ND A100 v4 Series. https:\/\/learn.microsoft.com\/en-us\/azure\/virtual-machines\/sizes\/gpu-accelerated\/nd-family#nd_a100_v4-series Accessed: 2025-01-30."},{"key":"e_1_3_3_1_36_2","unstructured":"Microsoft Industry Clouds. 2023. Evolving Microsoft Azure Data Manager for Agriculture to transform data into intuitive insights. https:\/\/azure.microsoft.com\/en-us\/blog\/evolving-microsoft-azure-data-manager-for-agriculture. Accessed: 2025-01-07."},{"key":"e_1_3_3_1_37_2","unstructured":"Mistral AI Team. 2025. Mistral Small 3. https:\/\/mistral.ai\/news\/mistral-small-3\/ Accessed 2025-01-30."},{"key":"e_1_3_3_1_38_2","unstructured":"Ollama. 2025. Get up and running with large language models. https:\/\/github.com\/ollama\/ollama. Accessed 2025-01-30."},{"key":"e_1_3_3_1_39_2","unstructured":"OpenAI. 2025. OpenAI API Pricing. https:\/\/openai.com\/api\/pricing\/ Accessed: 2025-01-30."},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Fernando\u00a0S Paolo David Kroodsma Jennifer Raynor Tim Hochberg Pete Davis Jesse Cleary Luca Marsaglia Sara Orofino Christian Thomas and Patrick Halpin. 2024. Satellite mapping reveals extensive industrial activity at sea. Nature 625 7993 (2024) 85\u201391.","DOI":"10.1038\/s41586-023-06825-8"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"crossref","unstructured":"Varatheepan Paramanayakam Andreas Karatzas Iraklis Anagnostopoulos and Dimitrios Stamoulis. 2024. Less is more: Optimizing function calling for llm execution on edge devices. arXiv preprint arXiv:2411.15399 (2024).","DOI":"10.23919\/DATE64628.2025.10992798"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.2905\/9F06F36F-4B11-47EC-ABB0-4F8B7B1D72EA"},{"key":"e_1_3_3_1_43_2","unstructured":"C Robinson R Gupta S Fobi\u00a0Nsutezo E Pound A Ortiz M Rosa K White R Dodhia A Zolli C Birge et\u00a0al. 2023. Turkey building damage assessment. Microsoft Corporation (2023). https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2023\/02\/Turkey-Earthquake-Report-2_MS.pdf"},{"key":"e_1_3_3_1_44_2","unstructured":"Jo\u00e3o\u00a0Daniel Silva Jo\u00e3o Magalh\u00e3es Devis Tuia and Bruno Martins. 2024. Large language models for captioning and retrieving remote sensing images. arXiv preprint arXiv:2402.06475 (2024)."},{"key":"e_1_3_3_1_45_2","unstructured":"Simranjit Singh Michael Fore and Dimitrios Stamoulis. 2024. Evaluating Tool-Augmented Agents in Remote Sensing Platforms. arXiv preprint arXiv:2405.00709 (2024)."},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00063"},{"key":"e_1_3_3_1_47_2","volume-title":"NeurIPS 2023 Foundation Models for Decision Making Workshop","author":"Srinivasan Venkat\u00a0Krishna","year":"2023","unstructured":"Venkat\u00a0Krishna Srinivasan, Zhen Dong, Banghua Zhu, Brian Yu, Damon Mosk-Aoyama, Kurt Keutzer, Jiantao Jiao, and Jian Zhang. 2023. Nexusraven: a commercially-permissive language model for function calling. In NeurIPS 2023 Foundation Models for Decision Making Workshop."},{"key":"e_1_3_3_1_48_2","unstructured":"Daniela Szwarcman Sujit Roy Paolo Fraccaro \u00deorsteinn\u00a0El\u00ed G\u00edslason Benedikt Blumenstiel Rinki Ghosal Pedro\u00a0Henrique de Oliveira Joao Lucas de\u00a0Sousa Almeida Rocco Sedona Yanghui Kang et\u00a0al. 2024. Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications. arXiv preprint arXiv:2412.02732 (2024)."},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","unstructured":"E. Vermote C. Justice M. Claverie and B. Franch. 2015. MOD09GA MODIS\/Terra Surface Reflectance Daily L2G Global 1km SIN Grid V006. 10.5067\/MODIS\/MOD09GA.006 Accessed 2025-01-07.","DOI":"10.5067\/MODIS\/MOD09GA.006"},{"key":"e_1_3_3_1_50_2","unstructured":"vLLM Team. 2025. vLLM Documentation. https:\/\/docs.vllm.ai\/en\/stable\/. Accessed: January 15 2025."},{"key":"e_1_3_3_1_51_2","doi-asserted-by":"publisher","DOI":"10.5555\/1208781"},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","unstructured":"Z. Wan S. Hook and G. Hulley. 2021. MODIS\/Terra Land Surface Temperature\/Emissivity 8-Day L3 Global 1km SIN Grid V061. 10.5067\/MODIS\/MYD11A2.061. Accessed 2025-01-07.","DOI":"10.5067\/MODIS\/MYD11A2.061"},{"key":"e_1_3_3_1_53_2","unstructured":"T Wolf. 2019. Huggingface\u2019s transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019)."},{"key":"e_1_3_3_1_54_2","unstructured":"Qingyun Wu Gagan Bansal Jieyu Zhang Yiran Wu Shaokun Zhang Erkang Zhu Beibin Li Li Jiang Xiaoyun Zhang and Chi Wang. 2023. Autogen: Enabling next-gen llm applications via multi-agent conversation framework. arXiv preprint arXiv:2308.08155 (2023)."},{"key":"e_1_3_3_1_55_2","volume-title":"First Conference on Language Modeling","author":"Wu Yiran","year":"2024","unstructured":"Yiran Wu, Tianwei Yue, Shaokun Zhang, Chi Wang, and Qingyun Wu. 2024. StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows. In First Conference on Language Modeling."},{"key":"e_1_3_3_1_56_2","unstructured":"Zhitong Xiong Yi Wang Fahong Zhang Adam\u00a0J Stewart Jo\u00eblle Hanna Damian Borth Ioannis Papoutsis Bertrand Le\u00a0Saux Gustau Camps-Valls and Xiao\u00a0Xiang Zhu. 2024. Neural plasticity-inspired foundation model for observing the Earth crossing modalities. arXiv e-prints (2024) arXiv\u20132403."},{"key":"e_1_3_3_1_57_2","unstructured":"An Yang Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chengyuan Li Dayiheng Liu Fei Huang Haoran Wei et\u00a0al. 2024. Qwen2. 5 Technical Report. arXiv preprint arXiv:2412.15115 (2024)."},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"crossref","unstructured":"Guofeng Yang Yu Li Yong He Zhenjiang Zhou Lingzhen Ye Hui Fang Yiqi Luo and Xuping Feng. 2024. Multimodal large language model for wheat breeding: a new exploration of smart breeding. arXiv preprint arXiv:2411.15203 (2024).","DOI":"10.1016\/j.isprsjprs.2025.03.027"},{"key":"e_1_3_3_1_59_2","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik Narasimhan and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)."},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3678717.3691308"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3678717.3691220"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"crossref","unstructured":"Chenhui Zhang and Sherrie Wang. 2024. Good at captioning bad at counting: Benchmarking gpt-4v on earth observation data. arXiv preprint arXiv:2401.17600 (2024).","DOI":"10.1109\/CVPRW63382.2024.00780"},{"key":"e_1_3_3_1_63_2","doi-asserted-by":"crossref","unstructured":"Wei Zhang Miaoxin Cai Tong Zhang Yin Zhuang and Xuerui Mao. 2024. EarthGPT: A Universal Multimodal Large Language Model for Multisensor Image Comprehension in Remote Sensing Domain. IEEE Transactions on Geoscience and Remote Sensing 62 (2024) 1\u201320.","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"e_1_3_3_1_64_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Zhou Shuyan","year":"2024","unstructured":"Shuyan Zhou, Frank\u00a0F. Xu, Hao Zhu, Xuhui Zhou, Robert Lo, Abishek Sridhar, Xianyi Cheng, Tianyue Ou, Yonatan Bisk, Daniel Fried, Uri Alon, and Graham Neubig. 2024. WebArena: A Realistic Web Environment for Building Autonomous Agents. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_3_1_65_2","unstructured":"Xiao\u00a0Xiang Zhu Zhitong Xiong Yi Wang Adam\u00a0J Stewart Konrad Heidler Yuanyuan Wang Zhenghang Yuan Thomas Dujardin Qingsong Xu and Yilei Shi. 2024. On the Foundations of Earth and Climate Foundation Models. arXiv preprint arXiv:2405.04285 (2024)."},{"key":"e_1_3_3_1_66_2","unstructured":"Yuchen Zhuang Yue Yu Kuan Wang Haotian Sun and Chao Zhang. 2023. Toolqa: A dataset for llm question answering with external tools. Advances in Neural Information Processing Systems 36 (2023) 50117\u201350143."}],"event":{"name":"COMPASS '25: ACM SIGCAS\/SIGCHI Conference on Computing and Sustainable Societies","location":"Toronto ON Canada","acronym":"COMPASS '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGCAS ACM Special Interest Group on Computers and Society"]},"container-title":["Proceedings of the ACM SIGCAS\/SIGCHI Conference on Computing and Sustainable Societies"],"original-title":[],"deposited":{"date-parts":[[2025,7,18]],"date-time":"2025-07-18T09:38:09Z","timestamp":1752831489000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3715335.3735494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,21]]},"references-count":65,"alternative-id":["10.1145\/3715335.3735494","10.1145\/3715335"],"URL":"https:\/\/doi.org\/10.1145\/3715335.3735494","relation":{},"subject":[],"published":{"date-parts":[[2025,7,21]]},"assertion":[{"value":"2025-07-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}