{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:53:13Z","timestamp":1781869993648,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,22]]},"DOI":"10.1145\/3744256.3812580","type":"proceedings-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:01:41Z","timestamp":1781866901000},"page":"92-102","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring LLM-Powered Agents for Modeling Thermal Dynamics of Buildings"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9260-8496","authenticated-orcid":false,"given":"Krzysztof","family":"Walczak","sequence":"first","affiliation":[{"name":"Amazon, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2948-9236","authenticated-orcid":false,"given":"Mario","family":"Berg\u00e9s","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, WA, USA and Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2012.6425995"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Klaus\u00a0Kaae Andersen Henrik Madsen and Lars\u00a0H Hansen. 2000. Modelling the heat dynamics of a building using stochastic differential equations. Energy and Buildings 31 1 (2000) 13\u201324.","DOI":"10.1016\/S0378-7788(98)00069-3"},{"key":"e_1_3_3_2_4_2","first-page":"173","volume-title":"Building Performance Analysis Conference and SimBuild: Co-organized by ASHRAE and IBPSA-USA","author":"Arendt Krzysztof","year":"2018","unstructured":"Krzysztof Arendt, Muhyiddine Jradi, Hamid\u00a0Reza Shaker, and Christian Veje. 2018. Comparative analysis of white-, gray-and black-box models for thermal simulation of indoor environment: Teaching building case study. In Building Performance Analysis Conference and SimBuild: Co-organized by ASHRAE and IBPSA-USA. ASHRAE, 173\u2013180."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Ercan Atam and Lieve Helsen. 2016. Control-Oriented Thermal Modeling of Multizone Buildings: Methods and Issues: Intelligent Control of a Building System. IEEE Control Systems Magazine 36 3 (2016) 86\u2013111. 10.1109\/MCS.2016.2535913","DOI":"10.1109\/MCS.2016.2535913"},{"key":"e_1_3_3_2_6_2","first-page":"1381","volume-title":"Building Simulation 2017","author":"Blum David\u00a0H","year":"2017","unstructured":"David\u00a0H Blum and Michael Wetter. 2017. MPCPy: An open-source software platform for model predictive control in buildings. In Building Simulation 2017 , Vol.\u00a015. IBPSA, 1381\u20131390."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Kathleen Champion Bethany Lusch J\u00a0Nathan Kutz and Steven\u00a0L Brunton. 2019. Data-driven discovery of coordinates and governing equations. Proceedings of the National Academy of Sciences 116 45 (2019) 22445\u201322451.","DOI":"10.1073\/pnas.1906995116"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Gaurav Chaudhary Hicham Johra Laurent Georges and Bj\u00f8rn Austb\u00f8. 2025. Transfer learning in building dynamics prediction. Energy and Buildings 330 (2025) 115384. 10.1016\/j.enbuild.2025.115384","DOI":"10.1016\/j.enbuild.2025.115384"},{"key":"e_1_3_3_2_9_2","unstructured":"Ziru Chen Shijie Chen Yuting Ning Qianheng Zhang Boshi Wang Botao Yu Yifei Li Zeyi Liao Chen Wei Zitong Lu et\u00a0al. 2024. Scienceagentbench: Toward rigorous assessment of language agents for data-driven scientific discovery. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.05080 (2024)."},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Drury\u00a0B. Crawley Linda\u00a0K. Lawrie Frederick\u00a0C. Winkelmann W.F. Buhl Y.Joe Huang Curtis\u00a0O. Pedersen Richard\u00a0K. Strand Richard\u00a0J. Liesen Daniel\u00a0E. Fisher Michael\u00a0J. Witte and Jason Glazer. 2001. EnergyPlus: creating a new-generation building energy simulation program. Energy and Buildings 33 4 (2001) 319\u2013331. 10.1016\/S0378-7788(00)00114-6Special Issue: BUILDING SIMULATION\u201999.","DOI":"10.1016\/S0378-7788(00)00114-6"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","unstructured":"J\u00e1n Drgo\u0148a Aaron\u00a0R. Tuor Vikas Chandan and Draguna\u00a0L. Vrabie. 2021. Physics-constrained deep learning of multi-zone building thermal dynamics. Energy and Buildings 243 (2021) 110992. 10.1016\/j.enbuild.2021.110992","DOI":"10.1016\/j.enbuild.2021.110992"},{"key":"e_1_3_3_2_12_2","unstructured":"Weihua Du Yiming Yang and Sean Welleck. 2025. Optimizing Temperature for Language Models with Multi-Sample Inference. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.05234 (2025)."},{"key":"e_1_3_3_2_13_2","unstructured":"ecobee. 2025. Donate Your Data. Retrieved September 7 2025 from https:\/\/www.ecobee.com\/en-us\/donate-your-data\/"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Zhen Fang Nicolas Crimier Lisa Scanu Alphanie Midelet Amr Alyafi and Benoit Delinchant. 2021. Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model. Energy and Buildings 245 (2021) 111053. 10.1016\/j.enbuild.2021.111053","DOI":"10.1016\/j.enbuild.2021.111053"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3679240.3734584"},{"key":"e_1_3_3_2_16_2","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Feng Mingquan","year":"2025","unstructured":"Mingquan Feng, Yixin Huang, Yizhou Liu, Bofang Jiang, and Junchi Yan. 2025. PhysPDE: Rethinking PDE discovery and a physical HYpothesis selection benchmark. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","unstructured":"Francesco Ferracuti Alessandro Fonti Lucio Ciabattoni Stefano Pizzuti Alessia Arteconi Lieve Helsen and Gabriele Comodi. 2017. Data-driven models for short-term thermal behaviour prediction in real buildings. Applied Energy 204 (2017) 1375\u20131387. 10.1016\/j.apenergy.2017.05.015","DOI":"10.1016\/j.apenergy.2017.05.015"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","unstructured":"Siddhartha Ghosh Steve Reece Alex Rogers Stephen Roberts Areej Malibari and Nicholas\u00a0R. Jennings. 2015. Modeling the Thermal Dynamics of Buildings: A Latent-Force- Model-Based Approach. ACM Trans. Intell. Syst. Technol. 6 1 Article 7 (March 2015) 27\u00a0pages. 10.1145\/2629674","DOI":"10.1145\/2629674"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Samuel Holt Tennison Liu and Mihaela van\u00a0der Schaar. 2024. Automatically learning hybrid digital twins of dynamical systems. Advances in Neural Information Processing Systems 37 (2024) 72170\u201372218.","DOI":"10.52202\/079017-2304"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Brent Huchuk Scott Sanner and William O\u2019Brien. 2022. Evaluation of data-driven thermal models for multi-hour predictions using residential smart thermostat data. Journal of Building Performance Simulation 15 4 (2022) 445\u2013464.","DOI":"10.1080\/19401493.2020.1864474"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData47090.2019.9006306"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"Kevin\u00a0J. Kircher and K. Max Zhang. 2015. On the lumped capacitance approximation accuracy in RC network building models. Energy and Buildings 108 (2015) 454\u2013462. 10.1016\/j.enbuild.2015.09.053","DOI":"10.1016\/j.enbuild.2015.09.053"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7525124"},{"key":"e_1_3_3_2_24_2","first-page":"139","volume-title":"Intelligent Building Control Systems: A Survey of Modern Building Control and Sensing Strategies","author":"Koeln Justin","year":"2017","unstructured":"Justin Koeln, Bryan Keating, Andrew Alleyne, Christopher Price, and Bryan\u00a0P Rasmussen. 2017. Multi-zone temperature modeling and control. In Intelligent Building Control Systems: A Survey of Modern Building Control and Sensing Strategies. Springer, 139\u2013166."},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","unstructured":"Julien Leprince Henrik Madsen Clayton Miller Jaume\u00a0Palmer Real Rik van der Vlist Kaustav Basu and Wim Zeiler. 2022. Fifty shades of grey: Automated stochastic model identification of building heat dynamics. Energy and Buildings 266 (2022) 112095. 10.1016\/j.enbuild.2022.112095","DOI":"10.1016\/j.enbuild.2022.112095"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","unstructured":"Han Li William O\u2019Brien Vivian Loftness Erica Cochran Hameen and Tianzhen Hong. 2025. A critical review of use cases and insights from a large dataset of smart thermostats. Advances in Applied Energy 19 (2025) 100236. 10.1016\/j.adapen.2025.100236","DOI":"10.1016\/j.adapen.2025.100236"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Han Li Giuseppe Pinto Marco\u00a0Savino Piscitelli Alfonso Capozzoli and Tianzhen Hong. 2024. Building thermal dynamics modeling with deep transfer learning using a large residential smart thermostat dataset. Engineering Applications of Artificial Intelligence 130 (2024) 107701. 10.1016\/j.engappai.2023.107701","DOI":"10.1016\/j.engappai.2023.107701"},{"key":"e_1_3_3_2_28_2","volume-title":"Ecobee donate your data 1,000 homes in 2017","author":"Luo Na","year":"2022","unstructured":"Na Luo and Tianzhen Hong. 2022. Ecobee donate your data 1,000 homes in 2017. Technical Report. Pacific Northwest National Lab.(PNNL), Richland, WA (United States)."},{"key":"e_1_3_3_2_29_2","series-title":"Proceedings of Machine Learning Research","first-page":"33940","volume-title":"Proceedings of the 41st International Conference on Machine Learning","volume":"235","author":"Ma Pingchuan","year":"2024","unstructured":"Pingchuan Ma, Tsun-Hsuan Wang, Minghao Guo, Zhiqing Sun, Joshua\u00a0B. Tenenbaum, Daniela Rus, Chuang Gan, and Wojciech Matusik. 2024. LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery. In Proceedings of the 41st International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol.\u00a0235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 33940\u201333962. https:\/\/proceedings.mlr.press\/v235\/ma24m.html"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Francesco Massa Gray and Michael Schmidt. 2018. A hybrid approach to thermal building modelling using a combination of Gaussian processes and grey-box models. Energy and Buildings 165 (2018) 56\u201363. 10.1016\/j.enbuild.2018.01.039","DOI":"10.1016\/j.enbuild.2018.01.039"},{"key":"e_1_3_3_2_31_2","unstructured":"Cl\u00e9mence M\u00e9tayer Annabelle Ballesta and Julien Martinelli. 2025. Data-driven Discovery of Digital Twins in Biomedical Research. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.21484 (2025)."},{"key":"e_1_3_3_2_32_2","unstructured":"Tung Nguyen Arsh Koneru Shufan Li and Aditya Grover. 2025. PhysiX: A Foundation Model for Physics Simulations. arxiv:https:\/\/arXiv.org\/abs\/2506.17774\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2506.17774"},{"key":"e_1_3_3_2_33_2","unstructured":"U.S.\u00a0Department of Energy. 2025. EnergyPlus. Retrieved September 7 2025 from https:\/\/energyplus.net\/"},{"key":"e_1_3_3_2_34_2","first-page":"4415","volume-title":"Advances in Neural Information Processing Systems 32","author":"Perslev Mathias","year":"2019","unstructured":"Mathias Perslev, Michael Jensen, Sune Darkner, Poul J\u00f8\u00a0rgen Jennum, and Christian Igel. 2019. U-Time: A Fully Convolutional Network for Time Series Segmentation Applied to Sleep Staging. In Advances in Neural Information Processing Systems 32, H.\u00a0Wallach, H.\u00a0Larochelle, A.\u00a0Beygelzimer, F.\u00a0d'Alch\u00e9-Buc, E.\u00a0Fox, and R.\u00a0Garnett (Eds.). Curran Associates, Inc., 4415\u20134426."},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","unstructured":"Giuseppe Pinto Riccardo Messina Han Li Tianzhen Hong Marco\u00a0Savino Piscitelli and Alfonso Capozzoli. 2022. Sharing is caring: An extensive analysis of parameter-based transfer learning for the prediction of building thermal dynamics. Energy and Buildings 276 (2022) 112530. 10.1016\/j.enbuild.2022.112530","DOI":"10.1016\/j.enbuild.2022.112530"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3679240.3734589"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Olaf Ronneberger Philipp Fischer and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015 (2015) 234\u2013241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","unstructured":"Elliott Skomski Cameron Rutherford Aaron Tuor Jan Drgona Elliott Skomski Soumya Vasisht and Draguna Vrabie. 2021. pnnl\/neuromancer. [Computer Software]. 10.11578\/dc.20240614.181","DOI":"10.11578\/dc.20240614.181"},{"key":"e_1_3_3_2_39_2","unstructured":"Thermal Energy\u00a0System Specialists. 2025. TRNSYS: Transient System Simulation Tool. Retrieved September 7 2025 from https:\/\/www.trnsys.com\/"},{"key":"e_1_3_3_2_40_2","first-page":"334","volume-title":"Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23-27, 2018","author":"Stoller Daniel","year":"2018","unstructured":"Daniel Stoller, Sebastian Ewert, and Simon Dixon. 2018. Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation. In Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23-27, 2018, Emilia G\u00f3mez, Xiao Hu, Eric Humphrey, and Emmanouil Benetos (Eds.). 334\u2013340."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Marius Tacke Matthias Busch Kartik Bali Kian Abdolazizi Kevin Linka Christian Cyron and Roland Aydin. 2025. Constitutive scientific generative agent (CSGA): Leveraging large language models for automated constitutive model discovery. Machine Learning for Computational Science and Engineering 1 1 (2025) 23.","DOI":"10.1007\/s44379-025-00022-2"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Charalampos Vallianos Andreas Athienitis and Benoit Delcroix. 2022. Automatic generation of multi-zone RC models using smart thermostat data from homes. Energy and Buildings 277 (2022) 112571. 10.1016\/j.enbuild.2022.112571","DOI":"10.1016\/j.enbuild.2022.112571"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","unstructured":"Charalampos Vallianos Jos\u00e9 Candanedo and Andreas Athienitis. 2023. Application of a large smart thermostat dataset for model calibration and Model Predictive Control implementation in the residential sector. Energy 278 (2023) 127839. 10.1016\/j.energy.2023.127839","DOI":"10.1016\/j.energy.2023.127839"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","unstructured":"Charalampos Vallianos Jos\u00e9 Candanedo and Andreas Athienitis. 2024. Thermal modeling for control applications of 60 000 homes in North America using smart thermostat data. Energy and Buildings 303 (2024) 113811. 10.1016\/j.enbuild.2023.113811","DOI":"10.1016\/j.enbuild.2023.113811"},{"key":"e_1_3_3_2_45_2","unstructured":"Florian Wiesner Matthias Wessling and Stephen Baek. 2025. Towards a Physics Foundation Model. arxiv:https:\/\/arXiv.org\/abs\/2509.13805\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2509.13805"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","unstructured":"Ziyao Yang Amol\u00a0D. Gaidhane J\u00e1n Drgo\u0148a Vikas Chandan Mahantesh\u00a0M. Halappanavar Frank Liu and Yu Cao. 2024. Physics-constrained graph modeling for building thermal dynamics. Energy and AI 16 (2024) 100346. 10.1016\/j.egyai.2024.100346","DOI":"10.1016\/j.egyai.2024.100346"},{"key":"e_1_3_3_2_47_2","series-title":"(CNS \u201918)","volume-title":"Proceedings of the Communications and Networking Symposium","author":"Yu Danilo","year":"2018","unstructured":"Danilo Yu, Abdolreza Abhari, Alan\u00a0S. Fung, Kaamran Raahemifar, and Farahnaz Mohammadi. 2018. Predicting indoor temperature from smart thermostat and weather forecast data. In Proceedings of the Communications and Networking Symposium (Baltimore, Maryland) (CNS \u201918). Society for Computer Simulation International, San Diego, CA, USA, Article 9, 12\u00a0pages."}],"event":{"name":"BuildSys '26: The 13th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation","location":"Banff Canada","acronym":"BuildSys '26","sponsor":["SIGEnergy ACM Special Interest Group on Energy Systems and Informatics"]},"container-title":["Proceedings of the 13th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation"],"original-title":[],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T11:28:23Z","timestamp":1781868503000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3744256.3812580"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":46,"alternative-id":["10.1145\/3744256.3812580","10.1145\/3744256"],"URL":"https:\/\/doi.org\/10.1145\/3744256.3812580","relation":{},"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"2026-06-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}