[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83085-en":3,"doc-seo-83085-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},83085,1099514067415,"Rowan","https://ap-avatar.wpscdn.com/avatar/100002539d78ffe74a7?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779092875211072502",8,"Research & Report","TopoBrick Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting","Building sensors are embedded in a physical topology, spatial hierarchy, and operational context, while most forecasting approaches either treat signals as isolated time series or use fixed covariate sets. TopoBrick introduces a training-free framework for zero-shot building IoT forecasting using building knowledge graphs to form a compact structural skeleton. An agentic topology sampler then selects target-specific exogenous variables, separated by deployment-time availability into past-known sensor states and future-known calendar, schedule, and meteorological inputs. Experiments on three real-world buildings show strong performance versus zero-shot foundations and competitive results with fully trained models, with topology-aware sampling beating random and fixed selection.","TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting  \nXiachong Lin  \n[dawn.lin@student.unsw.edu.au](dawn.lin@student.unsw.edu.au)[ ](dawn.lin@student.unsw.edu.au)University of New South Wales Sydney, NSW, Australia  \nDu Yin  \n[du.yin@unsw.edu.au](du.yin@unsw.edu.au)[ ](du.yin@unsw.edu.au)University of New South Wales Sydney, NSW, Australia  \nArian Prabowo  \n[arian.prabowo@unsw.edu.au](arian.prabowo@unsw.edu.au)[ ](arian.prabowo@unsw.edu.au)University of New South Wales Sydney, NSW, Australia  \nHao Xue  \n[haoxue@hkust-gz.edu.cn](haoxue@hkust-gz.edu.cn)[ ](haoxue@hkust-gz.edu.cn)Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China  \nWen Hu  \n[wen.hu@unsw.edu.au](wen.hu@unsw.edu.au)[ ](wen.hu@unsw.edu.au)University of New South Wales Sydney, NSW, Australia  \nImran Razzak [imran.razzak@mbzuai.ac.ae](imran.razzak@mbzuai.ac.ae)  \nMBZUAI Abu Dhabi, United Arab Emirates  \nMatthew Amos  \n[matt.amos@csiro.au](matt.amos@csiro.au)[ ](matt.amos@csiro.au)CSIRO Energy Centre Newcastle, NSW, Australia  \nSam Behrens  \n[sam.behrens@csiro.au](sam.behrens@csiro.au)[ ](sam.behrens@csiro.au)CSIRO Energy Centre Newcastle, NSW, Australia  \nFlora D. Salim  \n[flora.salim@unsw.edu.au](flora.salim@unsw.edu.au)[ ](flora.salim@unsw.edu.au)University of New South Wales Sydney, NSW, Australia  \narXiv :2607 .06349v 1 [ cs .AI ] 7 Jul 2026  \nAbstract  \nBuilding sensors are embedded in physical topology, spatial hierarchy, and operational context, yet existing forecasters often treat them as isolated time series or rely on fixed covariate sets. We present TopoBrick, a training-free framework for zero-shot building IoT (Internet-of-Things) forecasting. TopoBrick uses building knowledge graphs to construct a compact structural skeleton and employs an agentic topology sampler to select target-specific exogenous variables. The selected variables are organized by deploymenttime availability, separating past-known sensor states from futureknown calendar, schedule, and meteorological exogenous variables. Across three real-world buildings, TopoBrick outperforms strong zero-shot foundation-model baselines and remains competitive with fully trained building-specific models. Ablations show that topology-aware sampling is more reliable than random, ontologyonly, or fixed-hop selection, especially for physically coupled HVAC and weather-driven sensing variables. The code of this work is available in [https://github.com/Dawnlxc/TopoBrick.git](https://github.com/Dawnlxc/TopoBrick.git)  \nCCS Concepts  \n• Information systems → Spatial-temporal systems; • Computing methodologies → Machine learning; Knowledge representation and reasoning; • Computer systems organization → Sensor networks; • Applied computing → Engineering.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nConference acronym ’XX, Woodstock, NY  \n© 2018 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-1-4503-XXXX-X/2018/06  \n[https://doi.org/XXXXXXX.XXXXXXX](https://doi.org/XXXXXXX.XXXXXXX)  \nKeywords  \nBuilding IoT forecasting, building knowledge graph, zero-shot forecasting, topology-aware forecasting, Brick Schema  \nACM Reference Format:  \nXiachong Lin, Du Yin, Arian Prabowo, Hao Xue, Wen Hu, Imran Razzak, Matthew Amos, Sam Behrens, and Flora D. Salim. 2018. TopoBrick: Agentic Topology Sampling of Exogenous Variab","cbCaiu098Ah6b21a","https://ap.wps.com/l/cbCaiu098Ah6b21a","pdf",1710979,2,1,13,"English","en",105,"# Abstract\n# Introduction\n## Problem setting and motivation\n## Gaps in existing forecasting approaches\n# CCS Concepts\n# Keywords\n# References","[{\"question\":\"What problem does TopoBrick address in building IoT forecasting?\",\"answer\":\"TopoBrick targets the mismatch between how building sensors are embedded in physical topology and how existing methods typically treat sensors as independent channels or use fixed exogenous variable sets.\"},{\"question\":\"How does TopoBrick choose exogenous variables for a given target sensor?\",\"answer\":\"TopoBrick uses a building knowledge graph to build a compact structural skeleton, then applies an agentic topology sampler to select target-specific exogenous variables.\"},{\"question\":\"What types of exogenous variables does TopoBrick separate, and why?\",\"answer\":\"It organizes selected variables by deployment-time availability, separating past-known sensor states from future-known calendar, schedule, and meteorological variables to align with what is available at prediction time.\"}]",1784185095,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"topobrick-agentic-topology-sampling-of-exogenous-variables-for-zero-shot-building-iot-forecasting","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/topobrick-agentic-topology-sampling-of-exogenous-variables-for-zero-shot-building-iot-forecasting/83085/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does TopoBrick address in building IoT forecasting?","Question",{"text":75,"@type":76},"TopoBrick targets the mismatch between how building sensors are embedded in physical topology and how existing methods typically treat sensors as independent channels or use fixed exogenous variable sets.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does TopoBrick choose exogenous variables for a given target sensor?",{"text":80,"@type":76},"TopoBrick uses a building knowledge graph to build a compact structural skeleton, then applies an agentic topology sampler to select target-specific exogenous variables.",{"name":82,"@type":73,"acceptedAnswer":83},"What types of exogenous variables does TopoBrick separate, and why?",{"text":84,"@type":76},"It organizes selected variables by deployment-time availability, separating past-known sensor states from future-known calendar, schedule, and meteorological variables to align with what is available at prediction time.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]