{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T07:05:10Z","timestamp":1779779110940,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T00:00:00Z","timestamp":1780099200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,31]]},"DOI":"10.1145\/3814573.3814949","type":"proceedings-article","created":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T06:07:06Z","timestamp":1779775626000},"page":"28-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Human Mobility Prediction with Spatially Aware LLM-based Multi-Agent Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4994-7164","authenticated-orcid":false,"given":"Shangyu","family":"Lou","sequence":"first","affiliation":[{"name":"University of California, Santa Barbara, Santa Barbara, CA, USA and San Diego State University, San Diego, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6033-7912","authenticated-orcid":false,"given":"Ziqi","family":"Cui","sequence":"additional","affiliation":[{"name":"Politecnico di Milano, Milan, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,30]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0Feng H.\u00a0Lyu C.\u00a0Chen and Y.-S.\u00a0Ong. Where to Move Next: Zero-shot Generalization of LLMs for Next POI Recommendation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.01855 2024.","DOI":"10.1109\/CAI59869.2024.00277"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"M.\u00a0C. Gonz\u00e1lez C.\u00a0A. Hidalgo and A.-L. Barab\u00e1si. Understanding individual human mobility patterns. Nature 453(7196):779\u2013782 2008.","DOI":"10.1038\/nature06958"},{"key":"e_1_3_3_1_4_2","unstructured":"G.\u00a0He Z.\u00a0Zhuang C.\u00a0Li H.\u00a0Qiao S.\u00a0Feng H.\u00a0Wang F.\u00a0Li G.\u00a0Cong and X.\u00a0Li. A comprehensive survey of generative AI for POI recommendation. IEEE Transactions on Knowledge and Data Engineering 2025."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"K.\u00a0Janowicz S.\u00a0Gao G.\u00a0McKenzie Y.\u00a0Hu and B.\u00a0Bhaduri. GeoAI: Spatially explicit artificial intelligence techniques for geographic knowledge discovery and beyond. International Journal of Geographical Information Science 34(4):625\u2013636 2020.","DOI":"10.1080\/13658816.2019.1684500"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"K.\u00a0Janowicz Z.\u00a0Liu G.\u00a0Mai Z.\u00a0Wang I.\u00a0Majic A.\u00a0Fortacz G.\u00a0McKenzie and S.\u00a0Gao. Whose truth? Pluralistic geo-alignment for (agentic) AI. In Proc. ACM SIGSPATIAL 2025.","DOI":"10.1145\/3748636.3760465"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"crossref","unstructured":"I.\u00a0Jo and S.\u00a0W. Bednarz. Evaluating geography textbook questions from a spatial perspective: Using concepts of space tools of representation and cognitive processes to evaluate spatiality. Journal of Geography 108(1):4\u201313 2009. doi:10.1080\/00221340902758401.","DOI":"10.1080\/00221340902758401"},{"key":"e_1_3_3_1_8_2","unstructured":"Z.\u00a0Ke A.\u00a0Xu Y.\u00a0Ming X.-P. Nguyen C.\u00a0Xiong and S.\u00a0Joty. MAS-Zero: Designing multi-agent systems with zero supervision. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.14996 2025."},{"key":"e_1_3_3_1_9_2","unstructured":"Z.\u00a0Ke Y.\u00a0Ming A.\u00a0Xu R.\u00a0Chin X.-P. Nguyen P.\u00a0Jwalapuram S.\u00a0Yavuz C.\u00a0Xiong and S.\u00a0Joty. MAS-Orchestra: Understanding and improving multi-agent reasoning through holistic orchestration and controlled benchmarks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2601.14652 2026."},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0Li S.\u00a0Wang W.\u00a0Li S.\u00a0Liu and S.\u00a0Zhang. Predicting human mobility with federated learning. In Proc. ACM SIGSPATIAL 2020.","DOI":"10.1145\/3397536.3422270"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"crossref","unstructured":"X.\u00a0Li Y.\u00a0Ma Y.\u00a0Huang X.\u00a0Wang Y.\u00a0Lin and C.\u00a0Zhang. Synergized data efficiency and compression (SEC) optimization for large language models. In Proc. 4th International Conference on Electronic Information Engineering and Computer Science (EIECS) pages 586\u2013591 2024. doi:10.1109\/EIECS63941.2024.10800533.","DOI":"10.1109\/EIECS63941.2024.10800533"},{"key":"e_1_3_3_1_12_2","unstructured":"X.\u00a0Li F.\u00a0Huang J.\u00a0Lv Z.\u00a0Xiao G.\u00a0Li and Y.\u00a0Yue. Be more real: Travel diary generation using LLM agents and individual profiles. arXiv preprint 2025."},{"key":"e_1_3_3_1_13_2","unstructured":"X.\u00a0Li J.\u00a0Cao M.\u00a0Wang Y.\u00a0Wu L.\u00a0Yan Y.\u00a0Zhou Z.\u00a0Sha and Y.\u00a0Ma. FAST: A synergistic framework of attention and state-space models for spatiotemporal traffic prediction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2604.13453 2026."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Q.\u00a0Liu S.\u00a0Wu L.\u00a0Wang and T.\u00a0Tan. Predicting the next location: A recurrent model with spatial and temporal contexts. In Proc. AAAI Conference on Artificial Intelligence 2016.","DOI":"10.1609\/aaai.v30i1.9971"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"S.\u00a0Lou. Urban-MAS: Human-centered urban prediction with LLM-based multi-agent system. In Proc. 3rd ACM SIGSPATIAL International Workshop on Advances in Urban-AI pages 37\u201340 2025. doi:10.1145\/3764926.3771951.","DOI":"10.1145\/3764926.3771951"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Luo Q.\u00a0Liu and Z.\u00a0Liu. STAN: Spatio-temporal attention network for next location recommendation. In Proc. The Web Conference (WWW) 2021.","DOI":"10.1145\/3442381.3449998"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"G.\u00a0Mai C.\u00a0Cundy K.\u00a0Choi Y.\u00a0Hu N.\u00a0Lao and S.\u00a0Ermon. Towards a foundation model for geospatial artificial intelligence (vision paper). In Proceedings of the 30th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems 2022.","DOI":"10.1145\/3557915.3561043"},{"key":"e_1_3_3_1_18_2","unstructured":"R.\u00a0Manvi S.\u00a0Khanna M.\u00a0Burke D.\u00a0Lobell and S.\u00a0Ermon. Large language models are geographically biased. In Proc. ICML 2024."},{"key":"e_1_3_3_1_19_2","unstructured":"R.\u00a0Manvi S.\u00a0Khanna G.\u00a0Mai M.\u00a0Burke D.\u00a0Lobell and S.\u00a0Ermon. GeoLLM: Extracting geospatial knowledge from large language models. In Proc. ICLR 2024."},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"H.\u00a0J. Miller. Modelling accessibility using space-time prism concepts within geographical information systems. International Journal of Geographical Information Systems 5(3):287\u2013301 1991.","DOI":"10.1080\/02693799108927856"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"National Research Council. Learning to Think Spatially. The National Academies Press Washington DC 2006. doi:10.17226\/11019.","DOI":"10.17226\/11019"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"L.\u00a0Pappalardo F.\u00a0Simini S.\u00a0Rinzivillo D.\u00a0Pedreschi F.\u00a0Giannotti and A.-L. Barab\u00e1si. Returners and explorers dichotomy in human mobility. Nature Communications 6:8166 2015.","DOI":"10.1038\/ncomms9166"},{"key":"e_1_3_3_1_23_2","unstructured":"J.\u00a0Roberts T.\u00a0L\u00fcddecke S.\u00a0Das K.\u00a0Han and S.\u00a0Albanie. GPT4GEO: How a language model sees the world\u2019s geography. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2306.00020 2023."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"A.\u00a0Sevtsuk and M.\u00a0Mekonnen. Urban network analysis: A new toolbox for measuring city form in ArcGIS. Revue Internationale de G\u00e9omatique 22(2):287\u2013305 2012.","DOI":"10.3166\/rig.22.287-305"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"M.\u00a0D. Siampou S.-L. Hsu S.\u00a0Choudhury N.\u00a0Arora and C.\u00a0Shahabi. Toward foundation models for mobility enriched geospatially embedded objects. In Proc. ACM SIGSPATIAL 2025.","DOI":"10.1145\/3748636.3760459"},{"key":"e_1_3_3_1_26_2","unstructured":"V.\u00a0Venkataramani H.\u00a0Shi Z.\u00a0Ke A.\u00a0Xu X.\u00a0He Y.\u00a0Zhou S.\u00a0Yavuz H.\u00a0Wang and S.\u00a0Joty. MAS-ProVe: Understanding the process verification of multi-agent systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2602.03053 2026."},{"key":"e_1_3_3_1_27_2","unstructured":"D.\u00a0Wang S.\u00a0Gao C.\u00a0Huang Y.\u00a0Huang R.\u00a0Feng and S.\u00a0Shang. TOOL4POI: A tool-augmented LLM framework for next POI recommendation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2511.06405 2025."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"J.\u00a0Wang R.\u00a0Jiang C.\u00a0Yang Z.\u00a0Wu M.\u00a0Onizuka R.\u00a0Shibasaki N.\u00a0Koshizuka and C.\u00a0Xiao. Large language models as urban residents: An LLM agent framework for personal mobility generation. In Proc. NeurIPS 2024.","DOI":"10.52202\/079017-3957"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"X.\u00a0Wang T.\u00a0Cheng S.\u00a0Law Z.\u00a0Zeng I.\u00a0Ilyankou J.\u00a0Liu L.\u00a0Yin W.\u00a0Huang and N.\u00a0Jongwiriyanurak. Into the unknown: Applying inductive spatial-semantic location embeddings for predicting mobility beyond visited places. In Proc. ACM SIGSPATIAL 2025.","DOI":"10.1145\/3748636.3764175"},{"key":"e_1_3_3_1_30_2","unstructured":"X.\u00a0Wang M.\u00a0Fang Z.\u00a0Zeng and T.\u00a0Cheng. Where would I go next? Large language models as human mobility predictors. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.15197 2023."},{"key":"e_1_3_3_1_31_2","unstructured":"W.\u00a0Wongso H.\u00a0Xue and F.\u00a0D. Salim. Massive-STEPS: Massive semantic trajectories for understanding POI check-ins \u2013 dataset and benchmarks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.11239 2025."},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Wu Y.\u00a0Peng J.\u00a0Yu and R.\u00a0S.\u00a0T. Lee. MAS4POI: A multi-agents collaboration system for next POI recommendation. In Lecture Notes in Computer Science 2025.","DOI":"10.1007\/978-981-96-8180-8_28"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Yao Y.\u00a0Fu B.\u00a0Liu W.\u00a0Hu and H.\u00a0Xiong. Representing urban functions through zone embedding with human mobility patterns. In Proc. IJCAI 2018.","DOI":"10.24963\/ijcai.2018\/545"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Zhang X.\u00a0Ding Z.\u00a0Zhang and A.\u00a0Hajj-Ahmad. Enhancing point of interest search with semantic and spatial information. In Proc. ACM WWW 2025.","DOI":"10.1145\/3748636.3764606"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"crossref","unstructured":"P.\u00a0Zhao H.\u00a0Zhu Y.\u00a0Liu J.\u00a0Xu Z.\u00a0Li F.\u00a0Zhuang V.\u00a0S. Sheng and X.\u00a0Zhou. Where to go next: A spatio-temporal gated network for next POI recommendation. In Proc. AAAI Conference on Artificial Intelligence 2019.","DOI":"10.1609\/aaai.v33i01.33015877"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"crossref","unstructured":"L.\u00a0Zhong L.\u00a0Wang X.\u00a0Yang and Q.\u00a0Liao. CoMaPOI: A collaborative multi-agent framework for next POI prediction bridging the gap between trajectory and language. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.23837 2025.","DOI":"10.1145\/3726302.3729930"}],"event":{"name":"HILDA '26: Workshop on Human-In-the-Loop Data Analytics","location":"Bengaluru India","acronym":"HILDA '26","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Workshop on Human-In-the-Loop Data Analytics"],"original-title":[],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T06:56:56Z","timestamp":1779778616000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3814573.3814949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,30]]},"references-count":35,"alternative-id":["10.1145\/3814573.3814949","10.1145\/3814573"],"URL":"https:\/\/doi.org\/10.1145\/3814573.3814949","relation":{},"subject":[],"published":{"date-parts":[[2026,5,30]]},"assertion":[{"value":"2026-05-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}