{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T06:07:26Z","timestamp":1770962846381,"version":"3.50.1"},"reference-count":112,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72531008"],"award-info":[{"award-number":["72531008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018542","name":"Natural Science Foundation of Sichuan Province","doi-asserted-by":"publisher","award":["25NSFTD0032"],"award-info":[{"award-number":["25NSFTD0032"]}],"id":[{"id":"10.13039\/501100018542","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Research Fund of Kunming University of Science and Technology","award":["KKZ3202537094"],"award-info":[{"award-number":["KKZ3202537094"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Large language models (LLMs) are fundamentally transforming intelligent traffic systems by enabling semantic abstraction, probabilistic reasoning, and multimodal information fusion across heterogeneous data. This review examines existing research on LLM integration, ranging from data representation to autonomous agents, through an information-theoretic lens, conceptualizing LLMs as entropy-minimizing probabilistic systems that shape their capabilities in uncertainty modeling and semantic compression. We identify core integration patterns and analyze fundamental limitations arising from the inherent mismatch between discrete, entropy-driven LLM reasoning and the continuous, causal, and safety-critical nature of physical traffic environments. This reflects a deep structural tension rather than mere technical gaps. We delineate clear boundaries: LLMs are indispensable for managing high semantic entropy in tasks like contextual understanding and knowledge integration, whereas classical physics-based and optimization models remain essential in domains requiring ultra-low physical, temporal, and causal\/normative entropy, such as real-time control and safety verification. Finally, we propose a forward-looking research agenda centered on hybrid intelligence architectures that bridge semantic information processing with physical system modeling for next-generation traffic systems.<\/jats:p>","DOI":"10.3390\/e28020211","type":"journal-article","created":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T17:45:36Z","timestamp":1770831936000},"page":"211","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating Large Language Models into Traffic Systems: Integration Levels, Capability Boundaries, and an Information-Theoretic Perspective"],"prefix":"10.3390","volume":"28","author":[{"given":"Wenwen","family":"Tu","sequence":"first","affiliation":[{"name":"Engineering Training Center, Kunming University of Science and Technology, Kunming 650500, China"}]},{"given":"Junfan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence Industry, Kunming University of Science and Technology, Kunming 650500, China"}]},{"given":"Feng","family":"Xiao","sequence":"additional","affiliation":[{"name":"Business School, Sichuan University, Chengdu 610065, China"}]},{"given":"Xiaosa","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence Industry, Kunming University of Science and Technology, Kunming 650500, China"}]},{"given":"Yong","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence Industry, Kunming University of Science and Technology, Kunming 650500, China"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,11]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"105260","DOI":"10.1016\/j.trc.2025.105260","article-title":"TRIP: Transport reasoning with intelligence progression \u2014A foundation framework","volume":"179","author":"Liu","year":"2025","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"105325","DOI":"10.1016\/j.trc.2025.105325","article-title":"Traffic-IT: Enhancing traffic scene understanding for multimodal large language models","volume":"180","author":"Kuang","year":"2025","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_3","unstructured":"Le, D., Yunusoglu, A., Tiwari, K., Isik, M., and Dikmen, I. (2024). Multimodal LLM for intelligent transportation systems. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"113278","DOI":"10.1016\/j.asoc.2025.113278","article-title":"Integrating large language models with cross-modal data fusion for advanced intelligent transportation systems in sustainable cities development","volume":"177","author":"Jiang","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.tranpol.2024.03.006","article-title":"TrafficGPT: Viewing, processing and interacting with traffic foundation models","volume":"150","author":"Zhang","year":"2024","journal-title":"Transp. Policy"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, D., Jiang, B., Huang, L., Beigi, A., Zhao, C., Tan, Z., Bhattacharjee, A., Jiang, Y., Chen, C., and Wu, T. (2025, January 4\u20139). From Generation to Judgment: Opportunities and Challenges of LLM-as-a-Judge. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China.","DOI":"10.18653\/v1\/2025.emnlp-main.138"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Nam, D., Macvean, A., Hellendoorn, V., Vasilescu, B., and Myers, B. (2024, January 14\u201320). Using an LLM to Help with Code Understanding. Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering, Lisbon, Portugal.","DOI":"10.1145\/3597503.3639187"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"100211","DOI":"10.1016\/j.hcc.2024.100211","article-title":"A survey on large language model (LLM) security and privacy: The Good, The Bad, and The Ugly","volume":"4","author":"Yao","year":"2024","journal-title":"High-Confid. Comput."},{"key":"ref_9","first-page":"5539","article-title":"OpenAGI: When LLM meets domain experts","volume":"36","author":"Ge","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_10","unstructured":"Wu, S., Fei, H., Qu, L., Ji, W., and Chua, T.-S. (2024, January 21\u201327). Next-GPT: Any-To-Any Multimodal LLM. Proceedings of the 41st International Conference on Machine Learning, Vienna, Austria."},{"key":"ref_11","unstructured":"Guo, X., Zhang, Q., Jiang, J., Peng, M., Yang, H.F., and Zhu, M. (2026, February 06). Towards Responsible and Reliable Traffic Flow Prediction with Large Language Models. Available online: https:\/\/ssrn.com\/abstract=4805901."},{"key":"ref_12","first-page":"100030","article-title":"CrashSage: A large language model-centered framework for contextual and interpretable traffic crash analysis","volume":"3\u20134","author":"Zhen","year":"2025","journal-title":"Artif. Intell. Transp."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"464","DOI":"10.1016\/j.aej.2025.05.027","article-title":"TraffiCoT-R: A framework for advanced spatio-temporal reasoning in large language models","volume":"128","author":"Alsahfi","year":"2025","journal-title":"Alex. Eng. J."},{"key":"ref_14","unstructured":"Zheng, O., Abdel-Aty, M., Wang, D., Wang, Z., and Ding, S. (2023). ChatGPT is on the horizon: Could a large language model be suitable for intelligent traffic safety research and applications?. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wang, B., Cai, Z., Karim, M.M., Liu, C., and Wang, Y. (2024, January 24\u201327). Traffic Performance GPT (TP-GPT): Real-Time Data Informed Intelligent Chatbot for Transportation Surveillance and Management. Proceedings of the 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), Edmonton, AB, Canada.","DOI":"10.1109\/ITSC58415.2024.10919940"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Long, Q., Liu, S., Cao, N., Ren, Z., Ju, W., Fang, C., Zhu, Z., Zhu, H., and Zhou, Y. (2025). A survey of large language models for traffic forecasting: Methods and applications. arXiv.","DOI":"10.36227\/techrxiv.174495271.19469544\/v1"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"5674","DOI":"10.1109\/TITS.2025.3528116","article-title":"Integrating LLMs With ITS: Recent Advances, Potentials, Challenges, and Future Directions","volume":"26","author":"Mahmud","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, D., Zheng, H., Yue, W., and Wang, X. (2024). Advancing Its Applications with LLMs: A Survey on Traffic Management, Transportation Safety, and Autonomous Driving. International Joint Conference on Rough Sets, Springer.","DOI":"10.1007\/978-3-031-65668-2_20"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100116","DOI":"10.1016\/j.commtr.2023.100116","article-title":"GPT-4 enhanced multimodal grounding for autonomous driving: Leveraging cross-modal attention with large language models","volume":"4","author":"Liao","year":"2024","journal-title":"Commun. Transp. Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"105069","DOI":"10.1016\/j.trd.2025.105069","article-title":"VisionEV: Multimodal large language models for spatially aware electric vehicle charging demand prediction using satellite imagery","volume":"150","author":"Song","year":"2025","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"105368","DOI":"10.1016\/j.trc.2025.105368","article-title":"An explainable end-to-end autonomous driving framework based on large language model and vision modality fusion: Design and application of DriveLLM-V","volume":"181","author":"Hou","year":"2025","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"128736","DOI":"10.1016\/j.eswa.2025.128736","article-title":"LLM-augmented hierarchical reinforcement learning for human-like decision-making of autonomous driving","volume":"294","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_23","first-page":"100001","article-title":"Toward LLM-agent-based modeling of transportation systems: A conceptual framework","volume":"1","author":"Liu","year":"2025","journal-title":"Artif. Intell. Transp."},{"key":"ref_24","unstructured":"Wang, M., Pang, A., Kan, Y., Pun, M.-O., Chen, C.S., and Huang, B. (2024). LLM-assisted light: Leveraging large language model capabilities for human-mimetic traffic signal control in complex urban environments. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lai, S., Xu, Z., Zhang, W., Liu, H., and Xiong, H. (2025, January 3\u20137). LLMLight: Large language Models as Traffic Signal Control Agents. Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V 1, Toronto, ON, Canada.","DOI":"10.1145\/3690624.3709379"},{"key":"ref_26","first-page":"130555","article-title":"Traffic signal control at displaced left-turn intersections using an LLM-based actor-critic algorithm","volume":"301","author":"Uzelac","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Masri, S., Ashqar, H.I., and Elhenawy, M. (2025). Large Language Models (LLMs) as Traffic Control Systems at Urban Intersections: A New Paradigm. Vehicles, 7.","DOI":"10.3390\/vehicles7010011"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"100170","DOI":"10.1016\/j.commtr.2025.100170","article-title":"LC-LLM: Explainable lane-change intention and trajectory predictions with Large Language Models","volume":"5","author":"Peng","year":"2025","journal-title":"Commun. Transp. Res."},{"key":"ref_29","first-page":"6000","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"6999","DOI":"10.1109\/TNNLS.2021.3084827","article-title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects","volume":"33","author":"Li","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","article-title":"A comprehensive survey on graph neural networks","volume":"32","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"54608","DOI":"10.1109\/ACCESS.2024.3389497","article-title":"GPT (Generative Pre-Trained Transformer)\u2014A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions","volume":"12","author":"Yenduri","year":"2024","journal-title":"IEEE Access"},{"key":"ref_34","first-page":"101014","article-title":"Integrating large language models and affective computing for human-machine symbiosis in intelligent driving","volume":"6","author":"Dong","year":"2025","journal-title":"Innovation"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"101039","DOI":"10.1016\/j.tbs.2025.101039","article-title":"Where is morality on wheels? Decoding large language model (LLM)-driven decision in the ethical dilemmas of autonomous vehicles","volume":"40","author":"Xu","year":"2025","journal-title":"Travel Behav. Soc."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"104074","DOI":"10.1016\/j.tra.2024.104074","article-title":"Applying masked language model for transport mode choice behavior prediction","volume":"184","author":"Yang","year":"2024","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_37","unstructured":"Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., and Stoyanov, V. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"113210","DOI":"10.1016\/j.asoc.2025.113210","article-title":"Traffic scene perception via multimodal large language model with data augmentation and efficient training strategy","volume":"177","author":"Liu","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Wang, P., Wei, X., Hu, F., and Han, W. (2024, January 19\u201321). TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation. Proceedings of the 2024 International Conference on Computational Linguistics and Natural Language Processing (CLNLP), Yinchuan, China.","DOI":"10.1109\/CLNLP64123.2024.00026"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"108077","DOI":"10.1016\/j.aap.2025.108077","article-title":"When language and vision meet road safety: Leveraging multimodal large language models for video-based traffic accident analysis","volume":"219","author":"Zhang","year":"2025","journal-title":"Accid. Anal. Prev."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"de Zarz\u00e0, I., de Curt\u00f2, J., Roig, G., and Calafate, C.T. (2023). LLM multimodal traffic accident forecasting. Sensors, 23.","DOI":"10.3390\/s23229225"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Jeong, M., Chang, J., and Yoon, Y. (2025, January 3). Speak to Simulate: An LLM-Guided Agentic Framework for Traffic Simulation in SUMO. Proceedings of the GeoSIM \u201825: 8th ACM SIGSPATIAL International Workshop on Geospatial Simulation, Minneapolis, MN, USA.","DOI":"10.1145\/3764921.3770151"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"105307","DOI":"10.1016\/j.trc.2025.105307","article-title":"Agentic Large Language Models for day-to-day route choices","volume":"180","author":"Wang","year":"2025","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_44","first-page":"31","article-title":"Deep Learning and Clustering-Based Analysis of Text Narratives for Identification of Traffic Crash Severity Contributors","volume":"36","author":"Arteaga","year":"2023","journal-title":"Eng. Proc."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1007\/s13278-024-01278-x","article-title":"Utilizing the Twitter social media to identify transportation-related grievances in Indian cities","volume":"14","author":"Pullanikkat","year":"2024","journal-title":"Soc. Netw. Anal. Min."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"128609","DOI":"10.1016\/j.eswa.2025.128609","article-title":"UASeg: Uncertainty aware weakly supervised semantic segmentation for autonomous driving","volume":"292","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"105429","DOI":"10.1016\/j.trc.2025.105429","article-title":"Efficient 3D object annotation via vision-derived pseudo-LiDAR and Vision Language Model (VLM) validation","volume":"182","author":"Ma","year":"2025","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Yang, H., Wu, R., and Xu, W. (2024, January 18\u201322). TransCompressor: LLM-Powered Multimodal Data Compression for Smart Transportation. Proceedings of the ACM MobiCom \u201824: 30th Annual International Conference on Mobile Computing and Networking, Washington, DC, USA.","DOI":"10.1145\/3636534.3698120"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"111619","DOI":"10.1016\/j.asoc.2024.111619","article-title":"A semi-supervised mixture model of visual language multitask for vehicle recognition","volume":"159","author":"Liu","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_50","unstructured":"Huang, X. (2024). Enhancing traffic prediction with textual data using large language models. arXiv."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"113840","DOI":"10.1016\/j.asoc.2025.113840","article-title":"TPLLM: A traffic prediction framework based on pretrained Large Language Models","volume":"184","author":"Ma","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"129562","DOI":"10.1016\/j.neucom.2025.129562","article-title":"GPT4TFP: Spatio-temporal fusion large language model for traffic flow prediction","volume":"625","author":"Xu","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"130823","DOI":"10.1016\/j.physa.2025.130823","article-title":"Urban rail transit passenger flow prediction using large language model under multi-source spatiotemporal data fusion","volume":"675","author":"Ma","year":"2025","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Lee, X., and Gu, Y. (2024). Step-LLM: Spatial-Temporal-Enriched Prompting with Large Language Models for Traffic Prediction. International Conference of Electrical, Electronic and Networked Energy Systems, Springer.","DOI":"10.1007\/978-981-96-2080-7_26"},{"key":"ref_55","unstructured":"Tabassuma, S., Ahmeda, S., and Nowera, N. (2025, January 25). GAT-LLM: A Graph Attention-Based Framework with Large Language Models for Spatio-Temporal Traffic Forecasting. Proceedings of the ECAI 2025 Workshop ReLiT on Reasoning and Learning for Intelligent Transport, Bologna, Italy."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1109\/IOTM.001.2400047","article-title":"Large-Scale Traffic Flow Forecast with Lightweight LLM in Edge Intelligence","volume":"8","author":"Rong","year":"2024","journal-title":"IEEE Internet Things Mag."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"113174","DOI":"10.1016\/j.asoc.2025.113174","article-title":"LLM-TFP: Integrating large language models with spatio-temporal features for urban traffic flow prediction","volume":"177","author":"Cheng","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_58","doi-asserted-by":"crossref","unstructured":"Liu, C., Yang, S., Xu, Q., Li, Z., Long, C., Li, Z., and Zhao, R. (2024, January 24\u201327). Spatial-Temporal Large Language Model for Traffic Prediction. Proceedings of the 2024 25th IEEE International Conference on Mobile Data Management (MDM), Brussels, Belgium.","DOI":"10.1109\/MDM61037.2024.00025"},{"key":"ref_59","doi-asserted-by":"crossref","first-page":"105249","DOI":"10.1016\/j.trc.2025.105249","article-title":"A spatial\u2013Temporal Large Language Model with Denoising Diffusion Implicit for predictions in centralized multimodal transport systems","volume":"179","author":"Shao","year":"2025","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_60","unstructured":"Moghadas, S.M., Cornelis, B., Alahi, A., and Munteanu, A. (2024). Strada-LLM: Graph LLM for traffic prediction. arXiv."},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"103692","DOI":"10.1016\/j.inffus.2025.103692","article-title":"Spatio-temporal data fusion framework based on large language model for enhanced prediction of electric vehicle charging demand in smart grid management","volume":"126","author":"Shang","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_62","unstructured":"Hou, Y., Shao, Y., Han, Z., and Ye, Z. (2024, January 14\u201315). Construction and Application of Traffic Accident Knowledge Graph Based on LLM. Proceedings of the 2024 International Conference on Smart Transportation Interdisciplinary Studies, Nanjing, China."},{"key":"ref_63","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1111\/tgis.13064","article-title":"EVKG: An interlinked and interoperable electric vehicle knowledge graph for smart transportation system","volume":"27","author":"Qi","year":"2023","journal-title":"Trans. GIS"},{"key":"ref_64","doi-asserted-by":"crossref","first-page":"3915467","DOI":"10.1155\/2022\/3915467","article-title":"Analysis of Traffic Accident Based on Knowledge Graph","volume":"2022","author":"Zhang","year":"2022","journal-title":"J. Adv. Transp."},{"key":"ref_65","doi-asserted-by":"crossref","first-page":"106660","DOI":"10.1016\/j.ocecoaman.2023.106660","article-title":"Knowledge graph construction based on ship collision accident reports to improve maritime traffic safety","volume":"240","author":"Gan","year":"2023","journal-title":"Ocean Coast. Manag."},{"key":"ref_66","doi-asserted-by":"crossref","first-page":"104075","DOI":"10.1016\/j.tre.2025.104075","article-title":"Joint estimation and prediction of city-wide delivery demand: A large language model empowered graph-based learning approach","volume":"197","author":"Nie","year":"2025","journal-title":"Transp. Res. Part E Logist. Transp. Rev."},{"key":"ref_67","doi-asserted-by":"crossref","first-page":"125914","DOI":"10.1016\/j.eswa.2024.125914","article-title":"RAG-based explainable prediction of road users behaviors for automated driving using knowledge graphs and large language models","volume":"265","author":"Hussien","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_68","doi-asserted-by":"crossref","first-page":"113999","DOI":"10.1016\/j.asoc.2025.113999","article-title":"UPTM-LLM: Large language models-powered urban pedestrian travel modes recognition for intelligent transportation system","volume":"186","author":"Li","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_69","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, L., Wang, Y., Lin, H., Cheng, H., Liu, Z., He, L., and Wang, J. (2024). Controllable traffic simulation through LLM-guided hierarchical chain-of-thought reasoning. arXiv.","DOI":"10.1109\/IROS60139.2025.11247747"},{"key":"ref_70","unstructured":"Mo, B., Xu, H., Zhuang, D., Ma, R., Guo, X., and Zhao, J. (2023). Large language models for travel behavior prediction. arXiv."},{"key":"ref_71","doi-asserted-by":"crossref","first-page":"77456","DOI":"10.1109\/ACCESS.2025.3565297","article-title":"Large Language Models are Zero-Shot Next Location Predictors","volume":"13","author":"Beneduce","year":"2025","journal-title":"IEEE Access"},{"key":"ref_72","doi-asserted-by":"crossref","first-page":"104470","DOI":"10.1016\/j.trd.2024.104470","article-title":"ChatEV: Predicting electric vehicle charging demand as natural language processing","volume":"136","author":"Qu","year":"2024","journal-title":"Transp. Res. Part D Transp. Environ."},{"key":"ref_73","doi-asserted-by":"crossref","first-page":"100150","DOI":"10.1016\/j.commtr.2024.100150","article-title":"Towards explainable traffic flow prediction with large language models","volume":"4","author":"Guo","year":"2024","journal-title":"Commun. Transp. Res."},{"key":"ref_74","doi-asserted-by":"crossref","first-page":"111449","DOI":"10.1016\/j.cie.2025.111449","article-title":"LLM4PT: A large language model-based system for flexible and explainable public transit demand prediction","volume":"209","author":"Wu","year":"2025","journal-title":"Comput. Ind. Eng."},{"key":"ref_75","doi-asserted-by":"crossref","first-page":"12829","DOI":"10.1109\/TVT.2025.3551327","article-title":"LLM-Based Misbehavior Detection Architecture for Enhanced Traffic Safety in Connected Autonomous Vehicles","volume":"74","author":"Hu","year":"2025","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_76","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1109\/TIV.2024.3418522","article-title":"Traj-LLM: A New Exploration for Empowering Trajectory Prediction With Pre-Trained Large Language Models","volume":"10","author":"Lan","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_77","first-page":"1","article-title":"TransitTalk: Large language model-based digital assistants for enhancing transit customer experience and staff performance","volume":"9","author":"Wang","year":"2025","journal-title":"J. Intell. Transp. Syst."},{"key":"ref_78","doi-asserted-by":"crossref","first-page":"113919","DOI":"10.1016\/j.asoc.2025.113919","article-title":"Adaptive fault diagnosis of railway vehicle on-board controller with large language models","volume":"185","author":"Peng","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_79","doi-asserted-by":"crossref","first-page":"108178","DOI":"10.1016\/j.aap.2025.108178","article-title":"Assessing the efficacy of pre-trained large language models in analyzing autonomous vehicle field test disengagements","volume":"220","author":"Ansarinejad","year":"2025","journal-title":"Accid. Anal. Prev."},{"key":"ref_80","doi-asserted-by":"crossref","first-page":"113630","DOI":"10.1016\/j.knosys.2025.113630","article-title":"Large language model based system with causal inference and Chain-of-Thoughts reasoning for traffic scene risk assessment","volume":"319","author":"Zhong","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"ref_81","doi-asserted-by":"crossref","first-page":"105321","DOI":"10.1016\/j.trc.2025.105321","article-title":"VLM-RL: A unified vision language models and reinforcement learning framework for safe autonomous driving","volume":"180","author":"Huang","year":"2025","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_82","doi-asserted-by":"crossref","first-page":"104142","DOI":"10.1016\/j.tre.2025.104142","article-title":"Large language model-enhanced reinforcement learning for generic bus holding control strategies","volume":"200","author":"Yu","year":"2025","journal-title":"Transp. Res. Part E Logist. Transp. Rev."},{"key":"ref_83","doi-asserted-by":"crossref","first-page":"113333","DOI":"10.1016\/j.asoc.2025.113333","article-title":"Incorporating vision-based artificial intelligence and large language model for smart traffic light control","volume":"179","author":"Yao","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_84","doi-asserted-by":"crossref","unstructured":"Yin, Q., Xiong, Z., and Liu, Y. (2024). LLM-Enhanced Reinforcement Learning for Traffic Control at On-Ramp Merging Areas. International Conference on Artificial Intelligence and Autonomous Transportation, Springer.","DOI":"10.1007\/978-981-96-3965-6_38"},{"key":"ref_85","doi-asserted-by":"crossref","first-page":"105114","DOI":"10.1016\/j.robot.2025.105114","article-title":"HighwayLLM: Decision-making and navigation in highway driving with RL-informed language model","volume":"193","author":"Yildirim","year":"2025","journal-title":"Robot. Auton. Syst."},{"key":"ref_86","doi-asserted-by":"crossref","first-page":"1701","DOI":"10.1109\/TITS.2024.3498735","article-title":"The Crossroads of LLM and Traffic Control: A Study on Large Language Models in Adaptive Traffic Signal Control","volume":"26","author":"Movahedi","year":"2024","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_87","first-page":"82","article-title":"Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learning","volume":"38","author":"Da","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_88","doi-asserted-by":"crossref","first-page":"138786","DOI":"10.1016\/j.energy.2025.138786","article-title":"Optimal vehicle dynamics and powertrain control of carbon-free autonomous vehicles: Large language model assisted heterogeneous-agent learning","volume":"338","author":"Zhang","year":"2025","journal-title":"Energy"},{"key":"ref_89","doi-asserted-by":"crossref","first-page":"113917","DOI":"10.1016\/j.asoc.2025.113917","article-title":"Real-time traffic flow optimization using large language models and reinforcement learning for smart urban mobility","volume":"185","author":"Singh","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_90","doi-asserted-by":"crossref","unstructured":"Chen, X., and Meng, W. (July, January 30). LLM-Enhanced MARL for Smarter Traffic Control. Proceedings of the 2025 IEEE 19th International Conference on Control & Automation (ICCA), Tallinn, Estonia.","DOI":"10.1109\/ICCA65672.2025.11129767"},{"key":"ref_91","first-page":"100520","article-title":"Can language models be used for real-world urban-delivery route optimization?","volume":"4","author":"Liu","year":"2023","journal-title":"Innovation"},{"key":"ref_92","doi-asserted-by":"crossref","unstructured":"Manas, K., Zwicklbauer, S., and Paschke, A. (2024, January 2\u20135). TR2MTL: LLM based framework for Metric Temporal Logic Formalization of Traffic Rules. Proceedings of the 2024 IEEE Intelligent Vehicle Symposium (IV), Jeju Island, Republic of Korea.","DOI":"10.1109\/IV55156.2024.10588650"},{"key":"ref_93","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1109\/JRFID.2024.3384289","article-title":"Large Language Model-Assisted Arterial Traffic Signal Control","volume":"8","author":"Tang","year":"2024","journal-title":"IEEE J. Radio Freq. Identif."},{"key":"ref_94","doi-asserted-by":"crossref","unstructured":"Masri, S., Ashqar, H.I., and Elhenawy, M. (2024). Leveraging large language models (LLMs) for traffic management at urban intersections: The case of mixed traffic scenarios. arXiv.","DOI":"10.1109\/ICUFN65838.2025.11170100"},{"key":"ref_95","doi-asserted-by":"crossref","unstructured":"Percassi, F., and Vallati, M. (2025, January 20\u201323). Automated Planning for Urban Traffic Control with LLM-Generated Configurations. Proceedings of the International Florida Artificial Intelligence Research Society Conference, FLAIRS, Daytona Beach, FL, USA.","DOI":"10.32473\/flairs.38.1.138634"},{"key":"ref_96","doi-asserted-by":"crossref","unstructured":"Tang, Y., Dai, X., Zhao, C., Cheng, Q., and Lv, Y. (2024, January 1\u20132). Large Language Model-Driven Urban Traffic Signal Control. Proceedings of the 2024 Australian & New Zealand Control Conference (ANZCC), Gold Coast, Australia.","DOI":"10.1109\/ANZCC59813.2024.10432823"},{"key":"ref_97","first-page":"23721","article-title":"LLM-Powered Synthetic Environments for Self-Driving Scenarios","volume":"38","author":"Adekanye","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_98","doi-asserted-by":"crossref","unstructured":"Wang, X., Xu, L., Zhou, L., Liu, Y., Xiong, N., and Li, K.-C. (2025). Large language model-driven probabilistic trajectory prediction in the Internet of Things using spatio-temporal encoding and normalizing flows. Digit. Commun. Netw.","DOI":"10.1016\/j.dcan.2025.03.004"},{"key":"ref_99","doi-asserted-by":"crossref","first-page":"108299","DOI":"10.1016\/j.aap.2025.108299","article-title":"SafeDrive: Knowledge- and data-driven risk-sensitive decision-making for autonomous vehicles with Large Language Models","volume":"224","author":"Zhou","year":"2025","journal-title":"Accid. Anal. Prev."},{"key":"ref_100","doi-asserted-by":"crossref","unstructured":"Aiersilan, A., and Liu, M. (2024, January 6\u20138). LLM-enhanced traffic editor for accelerated testing of autonomous vehicles under various pedestrian behaviors. Proceedings of the International Conference on Smart Transportation and City Engineering (STCE 2024), Chongqing, China.","DOI":"10.1117\/12.3062033"},{"key":"ref_101","doi-asserted-by":"crossref","unstructured":"Yao, Y., Bhatnagar, S., Mazzola, M., Belagiannis, V., Gilitschenski, I., Palmieri, L., Razniewski, S., and Hallgarten, M. (2025). AGENTS-LLM: Augmentative Generation of Challenging Traffic Scenarios with an Agentic LLM Framework. arXiv.","DOI":"10.1109\/IROS60139.2025.11246348"},{"key":"ref_102","doi-asserted-by":"crossref","first-page":"2422","DOI":"10.3390\/smartcities7050095","article-title":"Multitask Learning for Crash Analysis: A Fine-Tuned LLM Framework Using Twitter Data","volume":"7","author":"Jaradat","year":"2024","journal-title":"Smart Cities"},{"key":"ref_103","doi-asserted-by":"crossref","first-page":"102880","DOI":"10.1016\/j.mex.2024.102880","article-title":"A method to promote safe cycling powered by large language models and AI agents","volume":"13","author":"Costa","year":"2024","journal-title":"MethodsX"},{"key":"ref_104","unstructured":"Zheng, O., Abdel-Aty, M., Wang, D., Wang, C., and Ding, S. (2023). TrafficSafetyGPT: Tuning a pre-trained large language model to a domain-specific expert in transportation safety. arXiv."},{"key":"ref_105","doi-asserted-by":"crossref","first-page":"104542","DOI":"10.1016\/j.tra.2025.104542","article-title":"Utilizing large language models to simulate parking search","volume":"199","author":"Fulman","year":"2025","journal-title":"Transp. Res. Part A Policy Pract."},{"key":"ref_106","doi-asserted-by":"crossref","first-page":"105940","DOI":"10.1016\/j.scs.2024.105940","article-title":"Large language model as parking planning agent in the context of mixed period of autonomous vehicles and Human-Driven vehicles","volume":"117","author":"Jin","year":"2024","journal-title":"Sustain. Cities Soc."},{"key":"ref_107","doi-asserted-by":"crossref","first-page":"127717","DOI":"10.1016\/j.eswa.2025.127717","article-title":"CCMA: A framework for cascading cooperative multi-agent in autonomous driving merging using Large Language Models","volume":"282","author":"Zhang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_108","doi-asserted-by":"crossref","first-page":"113625","DOI":"10.1016\/j.asoc.2025.113625","article-title":"DAPlanner: Dual-agent framework with multi-modal large language model for autonomous driving motion planning","volume":"183","author":"Zhang","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_109","doi-asserted-by":"crossref","unstructured":"Liu, X., Zou, B., and Aw, A. (2024, January 17\u201319). An NLP-Focused Pilot Training Agent for Safe and Efficient Aviation Communication. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Mexico City, Mexico.","DOI":"10.18653\/v1\/2024.naacl-industry.8"},{"key":"ref_110","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.trpro.2025.03.070","article-title":"Serendipity and LLM-based Recommender System for Smart Transportation","volume":"84","author":"Afridi","year":"2025","journal-title":"Transp. Res. Procedia"},{"key":"ref_111","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1016\/j.tranpol.2025.06.021","article-title":"Party politics in transport policy with a large language model","volume":"171","author":"Yun","year":"2025","journal-title":"Transp. Policy"},{"key":"ref_112","doi-asserted-by":"crossref","first-page":"100420","DOI":"10.1016\/j.array.2025.100420","article-title":"Context-aware decision making in autonomous vehicles: Integrating social behavior modeling with large language models","volume":"27","author":"Lamichhane","year":"2025","journal-title":"Array"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/2\/211\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T05:12:47Z","timestamp":1770959567000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/2\/211"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,11]]},"references-count":112,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["e28020211"],"URL":"https:\/\/doi.org\/10.3390\/e28020211","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,11]]}}}