pith. sign in

arxiv: 2606.00991 · v1 · pith:ZH45RJD3new · submitted 2026-05-31 · 💻 cs.AI

Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Support

Siyan Li , Zehao Wang , Jiachen Li , Kanok Boriboonsomsin , Matthew J. Barth , Guoyuan Wu This is my paper

Pith reviewed 2026-06-28 17:33 UTC · model grok-4.3

classification 💻 cs.AI
keywords large language modelsmulti-modal LLMstransportation systems managementTSMOdecision supportdata heterogeneityreal-time inferenceexplainability
0
0 comments X

The pith

LLMs serve best as a decision-support layer in transportation by integrating text, visual, and sensor inputs.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This review examines how large language models and multi-modal variants are being applied across transportation operations and services, mobility and fleet management, and data modeling for decision support. It separates practical operational deployments from early prototypes while highlighting recurring issues such as handling mixed data types, achieving real-time performance, and ensuring model explainability. The work concludes that these models show the greatest immediate value when used to fuse heterogeneous sources into operator-facing recommendations rather than as fully autonomous controllers.

Core claim

Using a PRISMA-guided screening of studies, the survey finds that LLM-based systems appear most promising as a decision-support layer, with multi-modal LLMs offering particular value when heterogeneous text, visual, and sensor inputs must be integrated.

What carries the argument

PRISMA-guided screening that categorizes applications into supply-side operations, demand-side mobility services, and data/modeling decision support while separating deployed uses from prototypes.

If this is right

  • Operators gain a unified interface for incident reports, camera feeds, and sensor streams without custom integration code for each modality.
  • Real-time inference constraints and governance requirements become the primary barriers to scaling beyond pilot projects.
  • Localized model adaptation and edge deployment are required before cross-agency data sharing can expand the training base.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Benchmarking suites focused on transportation-specific multi-modal tasks could accelerate identification of which model sizes deliver acceptable latency on roadside hardware.
  • Explainability tools developed for general LLMs may need domain-specific extensions to satisfy traffic operator audit requirements.
  • The same fusion capability that aids incident response could be tested on predictive fleet maintenance schedules using combined maintenance logs and vehicle telemetry.

Load-bearing premise

The PRISMA screening process captured a representative and unbiased sample of existing studies on LLM applications in transportation.

What would settle it

Discovery of a substantial body of operational LLM deployments in TSMO that were missed by the screening would show the synthesis does not reflect current practice.

Figures

Figures reproduced from arXiv: 2606.00991 by Guoyuan Wu, Jiachen Li, Kanok Boriboonsomsin, Matthew J. Barth, Siyan Li, Zehao Wang.

Figure 1
Figure 1. Figure 1: General operational cycle of TSMO. TSMO continuously senses transportation conditions, interprets system states, coordinates operational responses, [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: The development timeline of large language models up to August 2025 [12]. [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: An Example of MM-LLM architecture [18]. sensors, social media, GNSS devices, and incident reports, must be unified and analyzed in real time [26]. The real￾time processing of large datasets is also crucial for TSMO, as delays in data interpretation or decision-making can exacerbate congestion and lead to unsafe conditions, which is where MM￾LLMs can be leveraged. In this context, MM-LLMs offer considerable… view at source ↗
Figure 4
Figure 4. Figure 4: General organization of the paper. This survey paper is structured around two primary application domains, Transportation Operations & Services [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Key elements of an AI-driven TMC. Multi-modal data sources, including connected vehicles, sensors, social media, weather reports, incident [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Proposed workflow of an MM-LLM-enabled TSMO application. Multi-modal data sources are processed into structured context, combined with [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
read the original abstract

Transportation systems management and operations (TSMO) increasingly depends on timely interpretation of heterogeneous data, from various sensor streams, incident reports, traveler feedback, and visual observations. Large language models (LLMs), including emerging multi-modal large language models (MM-LLMs), provide a new mechanism for integrating these structured and unstructured inputs into operator-facing decision support. This survey paper reviews LLM- and MM-LLM-based applications in TSMO across three domains: transportation operations & services (supply), mobility & fleet services (demand), and data, modeling & decision support. Using a PRISMA-guided screening process, we synthesize current studies while distinguishing operationally oriented applications from prototype and emerging concepts. We further identify recurring challenges in data heterogeneity, real-time inference, explainability, multi-modal fusion, and governance. Finally, we outline existing gaps and future directions in localized adaptation, edge deployment, benchmarking, and cross-agency collaboration. Overall, LLM-based systems appear most promising as a decision-support layer, with MM-LLMs offering particular value when heterogeneous text, visual, and sensor inputs must be integrated.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. This survey paper reviews LLM- and MM-LLM-based applications in transportation systems management and operations (TSMO) across three domains (transportation operations & services, mobility & fleet services, and data/modeling/decision support). Using a PRISMA-guided screening process, it synthesizes studies while distinguishing operational applications from prototypes, identifies recurring challenges (data heterogeneity, real-time inference, explainability, multi-modal fusion, governance), outlines gaps and future directions (localized adaptation, edge deployment, benchmarking, cross-agency collaboration), and concludes that LLM-based systems appear most promising as a decision-support layer with MM-LLMs particularly valuable for integrating heterogeneous text, visual, and sensor inputs.

Significance. If the screened literature is representative, the paper provides a timely structured synthesis of an emerging intersection between large language models and transportation engineering. The explicit separation of operational versus prototype work and the enumeration of concrete challenges and gaps could usefully orient future research on edge deployment and benchmarking.

major comments (1)
  1. [Abstract] Abstract (and any dedicated Methods section): The PRISMA-guided screening process is invoked but supplies no search strings, databases queried, inclusion/exclusion criteria, or PRISMA flow numbers (studies screened, duplicates removed, full-text assessed, included). This information is required to evaluate whether the sample is representative and unbiased; its absence directly undermines the load-bearing claim that LLM-based systems 'appear most promising as a decision-support layer.'

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive comment on methodological transparency. We address the point below and will revise accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract (and any dedicated Methods section): The PRISMA-guided screening process is invoked but supplies no search strings, databases queried, inclusion/exclusion criteria, or PRISMA flow numbers (studies screened, duplicates removed, full-text assessed, included). This information is required to evaluate whether the sample is representative and unbiased; its absence directly undermines the load-bearing claim that LLM-based systems 'appear most promising as a decision-support layer.'

    Authors: We agree that the PRISMA details were omitted from the original submission, which limits the ability to assess representativeness. In the revised manuscript we will insert a dedicated Methods section (and update the abstract if needed) that explicitly reports the search strings, databases queried, inclusion/exclusion criteria, and a complete PRISMA flow diagram with the relevant counts. This addition will directly support the synthesis and the concluding claim by documenting the systematic selection process. The claim itself rests on patterns observed across the included studies (operational vs. prototype applications); supplying the screening details will strengthen rather than alter that assessment. revision: yes

Circularity Check

0 steps flagged

No circularity: literature review with no derivations

full rationale

This is a PRISMA-guided survey paper synthesizing existing LLM/MM-LLM studies in TSMO across three domains. It contains no equations, fitted parameters, predictions, uniqueness theorems, or derivation chains of any kind. The central claim that LLM-based systems appear most promising as a decision-support layer is an interpretive synthesis of reviewed literature rather than a result derived from the paper's own inputs or self-citations. No load-bearing step reduces to a self-definition or fitted input by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey paper, the work does not introduce or depend on free parameters, mathematical axioms, or invented entities in the sense of original research; it reviews prior studies.

pith-pipeline@v0.9.1-grok · 5744 in / 1065 out tokens · 24416 ms · 2026-06-28T17:33:40.342639+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

124 extracted references · 4 canonical work pages

  1. [1]

    A survey of intelligent transportation systems,

    S. H. An, B. H. Lee, and D. R. Shin, “A survey of intelligent transportation systems,”Proceedings - 3rd International Conference on Computational Intelligence, Communication Systems and Networks, CICSyN 2011, pp. 332–337, 2011

    2011

  2. [2]

    Advanced Learning Technologies for Intelligent Trans- portation Systems: Prospects and Challenges,

    R. A. Khalil, Z. Safelnasr, N. Yemane, M. Kedir, A. Shafiqurrahman, and N. Saeed, “Advanced Learning Technologies for Intelligent Trans- portation Systems: Prospects and Challenges,”IEEE Open Journal of Vehicular Technology, vol. 5, pp. 397–427, 2024

    2024

  3. [3]

    Metaverse for Intelligent Transportation Systems (ITS): A Comprehensive Review of Technologies, Applications, Implications, Challenges and Future Directions,

    D. S. Sarwatt, Y . Lin, J. Ding, Y . Sun, and H. Ning, “Metaverse for Intelligent Transportation Systems (ITS): A Comprehensive Review of Technologies, Applications, Implications, Challenges and Future Directions,”IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 7, pp. 6290–6308, 2024

    2024

  4. [4]

    Transportation Systems Manage- ment and Operations (TSMO)-Emphasis on Data-Driven Transportation Decisions Using Performance Measures,

    K. A. Abedi, J. A. Codjoe, J. Lee, M. J. Khattak, X. Sun, S. Mensah, I. A. Stantec, and M. Farmer-Kaiser, “Transportation Systems Manage- ment and Operations (TSMO)-Emphasis on Data-Driven Transportation Decisions Using Performance Measures,” 2024

    2024

  5. [5]

    Language Models are Few-Shot Learners,

    T. B. Brown, B. Mann, N. Ryder, M. Subbiah, J. Kaplan, P. Dhariwal, A. Neelakantan, P. Shyam, G. Sastry, A. Askell, S. Agarwal, A. Herbert-V oss, G. Krueger, T. Henighan, R. Child, A. Ramesh, D. M. Ziegler, J. Wu, C. Winter, C. Hesse, M. Chen, E. Sigler, M. Litwin, S. Gray, B. Chess, J. Clark, C. Berner, S. McCandlish, A. Radford, I. Sutskever, and D. Amo...

    Pith/arXiv arXiv 2020

  6. [6]

    Exploring the Potential of Large Language Models in Public Transportation: San Antonio Case Study,

    R. Jonnala, G. Liang, J. Yang, and I. Alsmadi, “Exploring the Potential of Large Language Models in Public Transportation: San Antonio Case Study,” 1 2025. [Online]. Available: http://arxiv.org/abs/2501.03904

    arXiv 2025

  7. [7]

    Transportation Systems Management and Operations Strategies — Organizing and Planning for Operations - FHW A Office of Operations,

    U. D. o. T. Federal Highway Administration, “Transportation Systems Management and Operations Strategies — Organizing and Planning for Operations - FHW A Office of Operations,” 5

  8. [8]

    Available: https://ops.fhwa.dot.gov/plan4ops/focus areas/integrating/operations strategies.htm

    [Online]. Available: https://ops.fhwa.dot.gov/plan4ops/focus areas/integrating/operations strategies.htm

  9. [9]

    The PRISMA 2020 statement: an updated guideline for reporting systematic reviews,

    M. J. Page, J. E. McKenzie, P. M. Bossuyt, I. Boutron, T. C. Hoffmann, C. D. Mulrow, L. Shamseer, J. M. Tetzlaff, E. A. Akl, S. E. Brennan, R. Chou, J. Glanville, J. M. Grimshaw, A. Hr ´objartsson, M. M. Lalu, T. Li, E. W. Loder, E. Mayo-Wilson, S. McDonald, L. A. McGuinness, L. A. Stewart, J. Thomas, A. C. Tricco, V . A. Welch, P. Whiting, and D. Moher, ...

    2020

  10. [10]

    The Handbook of Computational Linguistics and Natural Language Processing,

    A. Clark, C. Fox, and S. Lappin, “The Handbook of Computational Linguistics and Natural Language Processing,”The Handbook of Computational Linguistics and Natural Language Processing, 6 2010. [Online]. Available: https://onlinelibrary.wiley.com/doi/book/10.1002/ 9781444324044

    2010

  11. [11]

    LA VIS: A Library for Language-Vision Intelligence,

    D. Li, J. Li, H. Le, G. Wang, S. Savarese, and S. C. H. Hoi, “LA VIS: A Library for Language-Vision Intelligence,” 9 2022. [Online]. Available: http://arxiv.org/abs/2209.09019

    arXiv 2022

  12. [12]

    Attention Is All You Need,

    A. Vaswani, G. Brain, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention Is All You Need,” p. 1, 6 2017. [Online]. Available: https: //arxiv.org/pdf/1706.03762

    Pith/arXiv arXiv 2017

  13. [13]

    How Well Do LLMs Predict Prerequisite Skills? Zero-Shot Comparison to Expert-Defined Concepts,

    N. L. Le and M.-H. Abel, “How Well Do LLMs Predict Prerequisite Skills? Zero-Shot Comparison to Expert-Defined Concepts,” 7 2025. [Online]. Available: http://arxiv.org/abs/2507.18479

    arXiv 2025

  14. [14]

    BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,

    J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 1, pp. 4171–4186, 10 2018. [Online]. Availab...

    Pith/arXiv arXiv 2019

  15. [15]

    LLaMA: Open and Efficient Foundation Language Models,

    H. Touvron, T. Lavril, G. Izacard, X. Martinet, M.-A. Lachaux, T. Lacroix, B. Rozi `ere, N. Goyal, E. Hambro, F. Azhar, A. Rodriguez, A. Joulin, E. Grave, and G. Lample, “LLaMA: Open and Efficient Foundation Language Models,” 2 2023. [Online]. Available: https://arxiv.org/pdf/2302.13971

    Pith/arXiv arXiv 2023

  16. [16]

    Mamba: Linear-Time Sequence Modeling with Selective State Spaces,

    A. Gu and T. Dao, “Mamba: Linear-Time Sequence Modeling with Selective State Spaces,” 12 2023. [Online]. Available: https: //arxiv.org/pdf/2312.00752 15

    Pith/arXiv arXiv 2023

  17. [17]

    Llama 2: Open Foundation and Fine-Tuned Chat Models,

    H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y . Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale, D. Bikel, L. Blecher, C. C. Ferrer, M. Chen, G. Cucurull, D. Esiobu, J. Fernandes, J. Fu, W. Fu, B. Fuller, C. Gao, V . Goswami, N. Goyal, A. Hartshorn, S. Hosseini, R. Hou, H. Inan, M. Kardas, V . Kerkez, M. Khabsa, I. Kloumann, A. Koren...

    Pith/arXiv arXiv 2023

  18. [18]

    A Survey of Large Language Models,

    W. X. Zhao, K. Zhou, J. Li, T. Tang, X. Wang, Y . Hou, Y . Min, B. Zhang, J. Zhang, Z. Dong, Y . Du, C. Yang, Y . Chen, Z. Chen, J. Jiang, R. Ren, Y . Li, X. Tang, Z. Liu, P. Liu, J.-Y . Nie, and J.-R. Wen, “A Survey of Large Language Models,” arXiv preprint arXiv:2303.18223, 3 2023. [Online]. Available: https://arxiv.org/pdf/2303.18223

    Pith/arXiv arXiv 2023

  19. [19]

    A Survey on Multimodal Large Language Models,

    S. Yin, C. Fu, S. Zhao, K. Li, X. Sun, T. Xu, and E. Chen, “A Survey on Multimodal Large Language Models,”National Science Review, vol. 11, no. 12, 6 2023. [Online]. Available: https://arxiv.org/pdf/2306.13549

    Pith/arXiv arXiv 2023

  20. [20]

    A Comprehensive Overview of Large Language Models,

    H. Naveed, A. U. Khan, S. Qiu, M. Saqib, S. Anwar, M. Usman, N. Akhtar, N. Barnes, and A. Mian, “A Comprehensive Overview of Large Language Models,”ACM Transactions on Intelligent Systems and Technology, vol. 16, no. 5, 8 2025. [Online]. Available: /doi/pdf/10.1145/3744746?download=true

    work page doi:10.1145/3744746 2025

  21. [21]

    Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality,

    T. Dao and A. Gu, “Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality,” 5

  22. [22]

    Available: http://arxiv.org/abs/2405.21060

    [Online]. Available: http://arxiv.org/abs/2405.21060

    Pith/arXiv arXiv

  23. [23]

    Embracing Large Language Models in Traffic Flow Forecasting,

    Y . Zhao, X. Luo, H. Wen, Z. Xiao, W. Ju, and M. Zhang, “Embracing Large Language Models in Traffic Flow Forecasting,” 12 2024. [Online]. Available: http://arxiv.org/abs/2412.12201

    arXiv 2024

  24. [24]

    Casscetta,Transportation Systems Analysis: Models and Applications, 2009, vol

    E. Casscetta,Transportation Systems Analysis: Models and Applications, 2009, vol. 2. [Online]. Available: https://books.google.com/books?hl=en&lr=&id=AbU69bKmVScC& oi=fnd&pg=PR5&dq=transportation+systems+management+and+ operations&ots=wUu7rUkBUl&sig=VnAmoO3lkP-Ed0UuE0i3rKc tSs#v=onepage&q=transportation%20systems%20management% 20and%20operations&f=false

    2009

  25. [25]

    Intelligent transportation systems: Systems based on cognitive networking principles and man- agement functionality,

    G. Dimitrakopoulos and P. Demestichas, “Intelligent transportation systems: Systems based on cognitive networking principles and man- agement functionality,”IEEE Vehicular Technology Magazine, vol. 5, no. 1, pp. 77–84, 3 2010

    2010

  26. [26]

    Applying Transportation Systems Management and Operations (TSMO) to Rural Areas,

    E. Birriel, D. Mitchell, V . Sullivan, J. Peters, I. Leidos, and D. Associates, “Applying Transportation Systems Management and Operations (TSMO) to Rural Areas,” 10 2022. [Online]. Available: https://rosap.ntl.bts.gov/view/dot/64640

    2022

  27. [27]

    Transportation Systems Management and Operations (TSMO) in Smart Connected Communi- ties,

    U. D. o. T. Federal Highway Administration, “Transportation Systems Management and Operations (TSMO) in Smart Connected Communi- ties,” Tech. Rep., 12 2018

    2018

  28. [28]

    Large models in transportation infrastructure: a perspective,

    Y . Du, “Large models in transportation infrastructure: a perspective,” Intelligent Transportation Infrastructure, vol. 3, 2024

    2024

  29. [29]

    Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions,

    D. Mahmud, H. Hajmohamed, S. Almentheri, S. Alqaydi, L. Aldhaheri, R. A. Khalil, and N. Saeed, “Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directions,” 1 2025. [Online]. Available: http://arxiv.org/abs/2501.04437

    arXiv 2025

  30. [30]

    Large Language Models for Intelligent Transportation: A Review of the State of the Art and Challenges,

    S. Wandelt, C. Zheng, S. Wang, Y . Liu, and X. Sun, “Large Language Models for Intelligent Transportation: A Review of the State of the Art and Challenges,” 9 2024

    2024

  31. [31]

    Large models for intelligent transportation systems and autonomous vehicles: A survey,

    L. Gan, W. Chu, G. Li, X. Tang, and K. Li, “Large models for intelligent transportation systems and autonomous vehicles: A survey,” 10 2024

    2024

  32. [32]

    A Survey on the Ap- plications of Frontier AI, Foundation Models, and Large Language Models to Intelligent Transportation Systems,

    M. R. Shoaib, H. M. Emara, and J. Zhao, “A Survey on the Ap- plications of Frontier AI, Foundation Models, and Large Language Models to Intelligent Transportation Systems,” inICCA 2023 - 2023 5th International Conference on Computer and Applications, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023

    2023

  33. [33]

    Visual Mamba: A Survey and New Outlooks,

    R. Xu, S. Yang, Y . Wang, Y . Cai, B. Du, and H. Chen, “Visual Mamba: A Survey and New Outlooks,” 11 2024. [Online]. Available: http://arxiv.org/abs/2404.18861

    arXiv 2024

  34. [34]

    Multimodal LLM for Intelligent Transportation Systems,

    D. Le, A. Yunusoglu, K. Tiwari, M. Isik, and I. C. Dikmen, “Multimodal LLM for Intelligent Transportation Systems,” 12 2024. [Online]. Available: http://arxiv.org/abs/2412.11683

    arXiv 2024

  35. [35]

    LLM4Drive: A Survey of Large Language Models for Autonomous Driving,

    Z. Yang, X. Jia, H. Li, and J. Yan, “LLM4Drive: A Survey of Large Language Models for Autonomous Driving,” 8 2024. [Online]. Available: http://arxiv.org/abs/2311.01043

    arXiv 2024

  36. [36]

    A Survey on Multimodal Large Language Models for Autonomous Driving,

    C. Cui, Y . Ma, X. Cao, W. Ye, Y . Zhou, K. Liang, J. Chen, J. Lu, Z. Yang, K.-D. Liao, T. Gao, E. Li, K. Tang, Z. Cao, T. Zhou, A. Liu, X. Yan, S. Mei, J. Cao, Z. Wang, and C. Zheng, “A Survey on Multimodal Large Language Models for Autonomous Driving,” 11

  37. [37]

    Available: http://arxiv.org/abs/2311.12320

    [Online]. Available: http://arxiv.org/abs/2311.12320

    arXiv

  38. [38]

    Generative AI for Autonomous Driving: Frontiers and Opportunities,

    Y . Wang, S. Xing, C. Can, R. Li, H. Hua, K. Tian, Z. Mo, X. Gao, K. Wu, S. Zhou, H. You, J. Peng, J. Zhang, Z. Wang, R. Song, M. Yan, W. Zimmer, X. Zhou, P. Li, Z. Lu, C.-J. Chen, Y . Huang, R. A. Rossi, L. Sun, H. Yu, Z. Fan, F. H. Yang, Y . Kang, R. Greer, C. Liu, E. H. Lee, X. Di, X. Ye, L. Ren, A. Knoll, X. Li, S. Ji, M. Tomizuka, M. Pavone, T. Yang,...

    arXiv 2025

  39. [39]

    Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks,

    M. A. M. Dona, B. Cabrero-Daniel, Y . Yu, and C. Berger, “Evaluating and Enhancing Trustworthiness of LLMs in Perception Tasks,” 7

  40. [40]

    Available: http://arxiv.org/abs/2408.01433

    [Online]. Available: http://arxiv.org/abs/2408.01433

    arXiv

  41. [41]

    Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning,

    M. Villarreal, B. Poudel, and W. Li, “Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning,”IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC, pp. 3749–3755, 6 2023. [Online]. Available: https://arxiv.org/pdf/2306.08094

    arXiv 2023

  42. [42]

    H. Xu, J. Yuan, A. Zhou, G. Xu, W. Li, X. Ban, and X. Ye, “GenAI-powered Multi-Agent Paradigm for Smart Urban Mobility: Opportunities and Challenges for Integrating Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) with Intelligent Transportation Systems,” 9 2024. [Online]. Available: http://arxiv.org/abs/2409.00494

    arXiv 2024

  43. [43]

    Open-ti: open traffic intelligence with augmented language model,

    L. Da, K. Liou, T. Chen, X. Zhou, X. Luo, Y . Yang, and H. Wei, “Open-ti: open traffic intelligence with augmented language model,” International Journal of Machine Learning and Cybernetics, vol. 15, no. 10, pp. 4761–4786, 10 2024

    2024

  44. [44]

    Traffic accident detection and condition analysis based on social networking data,

    F. Ali, A. Ali, M. Imran, R. A. Naqvi, M. H. Siddiqi, and K. S. Kwak, “Traffic accident detection and condition analysis based on social networking data,”Accident Analysis & Prevention, vol. 151, p. 105973, 3 2021. [Online]. Available: https: //www.sciencedirect.com/science/article/abs/pii/S000145752100004X

    2021

  45. [45]

    Empowering real- time traffic reporting systems with NLP-Processed social media data,

    X. Wan, M. C. Lucic, H. Ghazzai, and Y . Massoud, “Empowering real- time traffic reporting systems with NLP-Processed social media data,” IEEE Open Journal of Intelligent Transportation Systems, vol. 1, pp. 159–175, 2020

    2020

  46. [46]

    Traffic Performance GPT (TP-GPT): Real-Time Data Informed Intelligent ChatBot for Transportation Surveillance and Management,

    B. Wang, Z. Cai, M. M. Karim, C. Liu, and Y . Wang, “Traffic Performance GPT (TP-GPT): Real-Time Data Informed Intelligent ChatBot for Transportation Surveillance and Management,” 5 2024. [Online]. Available: https://arxiv.org/pdf/2405.03076v1

    arXiv 2024

  47. [47]

    AI-Integrated Traffic Information System: A Synergistic Approach of Physics Informed Neural Network and GPT-4 for Traffic Estimation and Real-Time Assistance,

    T. Syum Gebre, L. Beni, E. Tsehaye Wasehun, and F. Elikem Dorbu, “AI-Integrated Traffic Information System: A Synergistic Approach of Physics Informed Neural Network and GPT-4 for Traffic Estimation and Real-Time Assistance,”IEEE Access, vol. 12, pp. 65 869–65 882, 2024

    2024

  48. [48]

    Strada-LLM: Graph LLM for traffic prediction,

    S. M. Moghadas, Y . Lyu, B. Cornelis, A. Alahi, and A. Munteanu, “Strada-LLM: Graph LLM for traffic prediction,” 2 2025. [Online]. Available: http://arxiv.org/abs/2410.20856

    arXiv 2025

  49. [49]

    Towards Explainable Traffic Flow Prediction with Large Language Models,

    X. Guo, Q. Zhang, J. Jiang, M. Peng, H. Yang, and M. Zhu, “Towards Explainable Traffic Flow Prediction with Large Language Models,” 9

  50. [50]

    Available: https://arxiv.org/pdf/2404.02937v3

    [Online]. Available: https://arxiv.org/pdf/2404.02937v3

    arXiv

  51. [51]

    TrafficGPT: Viewing, processing and interacting with traffic foundation models,

    S. Zhang, D. Fu, W. Liang, Z. Zhang, B. Yu, P. Cai, and B. Yao, “TrafficGPT: Viewing, processing and interacting with traffic foundation models,”Transport Policy, vol. 150, pp. 95–105, 5 2024. [Online]. Available: https://www.sciencedirect.com/science/article/abs/ pii/S0967070X24000726

    2024

  52. [52]

    Spatial- Temporal Large Language Model for Traffic Prediction,

    C. Liu, S. Yang, Q. Xu, Z. Li, C. Long, Z. Li, and R. Zhao, “Spatial- Temporal Large Language Model for Traffic Prediction,”Proceedings - IEEE International Conference on Mobile Data Management, pp. 31–40, 1 2024. [Online]. Available: https://arxiv.org/pdf/2401.10134

    arXiv 2024

  53. [53]

    TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation,

    P. Wang, X. Wei, F. Hu, and W. Han, “TransGPT: Multi-modal Generative Pre-trained Transformer for Transportation,”Proceedings - 2024 International Conference on Computational Linguistics and Natural Language Processing, CLNLP 2024, pp. 96–100, 2 2024. [Online]. Available: https://arxiv.org/pdf/2402.07233

    arXiv 2024

  54. [54]

    Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference,

    H. Zhen, Y . Shi, Y . Huang, J. J. Yang, and N. Liu, “Leveraging Large Language Models with Chain-of-Thought and Prompt Engineering for Traffic Crash Severity Analysis and Inference,” 8 2024. [Online]. Available: https://arxiv.org/pdf/2408.04652 16

    arXiv 2024

  55. [55]

    IncidentResponseGPT: Generating Traffic Incident Response Plans with Generative Artificial Intelligence,

    A. Grigorev, A.-S. M. K. Saleh, and Y . Ou, “IncidentResponseGPT: Generating Traffic Incident Response Plans with Generative Artificial Intelligence,” 4 2024. [Online]. Available: https://arxiv.org/pdf/2404. 18550

    2024

  56. [56]

    AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-modal Large Model,

    L. Wang, Y . Ren, H. Jiang, P. Cai, D. Fu, T. Wang, Z. Cui, H. Yu, X. Wang, H. Zhou, H. Huang, and Y . Wang, “AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-modal Large Model,” 12 2023. [Online]. Available: https://arxiv.org/pdf/2312.13156

    arXiv 2023

  57. [57]

    TrafficSafetyGPT: Tuning a Pre-trained Large Language Model to a Domain-Specific Expert in Transportation Safety,

    O. Zheng, M. Abdel-Aty, D. Wang, C. Wang, and S. Ding, “TrafficSafetyGPT: Tuning a Pre-trained Large Language Model to a Domain-Specific Expert in Transportation Safety,” 7 2023. [Online]. Available: https://arxiv.org/pdf/2307.15311

    arXiv 2023

  58. [58]

    Gen-AI for TSMO Knowledge Management,

    S. Somvanshi, J. Liu, and S. Das, “Gen-AI for TSMO Knowledge Management,” 12 2024. [Online]. Available: https://papers.ssrn.com/ abstract=5049945

    2024

  59. [59]

    Leveraging Large Language Models (LLMs) for Traffic Management at Urban Intersections: The Case of Mixed Traffic Scenarios,

    S. Masri, H. I. Ashqar, and M. Elhenawy, “Leveraging Large Language Models (LLMs) for Traffic Management at Urban Intersections: The Case of Mixed Traffic Scenarios,” 8 2024. [Online]. Available: https://arxiv.org/pdf/2408.00948

    arXiv 2024

  60. [60]

    iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement,

    A. Pang, M. Wang, M.-O. Pun, C. S. Chen, and X. Xiong, “iLLM-TSC: Integration reinforcement learning and large language model for traffic signal control policy improvement,” 7 2024. [Online]. Available: https://arxiv.org/pdf/2407.06025

    arXiv 2024

  61. [61]

    LLMLight: Large Language Models as Traffic Signal Control Agents,

    S. Lai, Z. Xu, W. Zhang, H. Liu, and H. Xiong, “LLMLight: Large Language Models as Traffic Signal Control Agents,” 12 2024. [Online]. Available: https://arxiv.org/pdf/2312.16044v1

    arXiv 2024

  62. [62]

    Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation,

    J. Wang, R. Jiang, C. Yang, Z. Wu, M. Onizuka, R. Shibasaki, N. Koshizuka, and C. Xiao, “Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation,”Advances in Neural Information Processing Systems, vol. 37, 2 2024. [Online]. Available: https://arxiv.org/pdf/2402.14744

    arXiv 2024

  63. [63]

    Exploring traffic accident locations from natural language based on spatial information retrieval,

    S. Wang, H. Dong, Y . Zhou, L. Jia, and Y . Qin, “Exploring traffic accident locations from natural language based on spatial information retrieval,”Proceedings of the 29th Chinese Control and Decision Conference, CCDC 2017, pp. 3490–3495, 7 2017

    2017

  64. [64]

    WEDGE: A multi-weather autonomous driving dataset built from generative vision- language models,

    A. Marathe, D. Ramanan, R. Walambe, and K. Kotecha, “WEDGE: A multi-weather autonomous driving dataset built from generative vision- language models,”IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, vol. 2023-June, pp. 3318– 3327, 5 2023. [Online]. Available: https://arxiv.org/pdf/2305.07528

    arXiv 2023

  65. [65]

    CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics,

    K. Yin, C. Liu, A. Mostafavi, and X. Hu, “CrisisSense-LLM: Instruction Fine-Tuned Large Language Model for Multi-label Social Media Text Classification in Disaster Informatics,” 6 2024. [Online]. Available: https://arxiv.org/pdf/2406.15477

    arXiv 2024

  66. [66]

    Large Language Models for Traffic and Transportation Research: Methodologies, State of the Art, and Future Opportunities,

    Y . Yan, Y . Liao, G. Xu, R. Yao, H. Fan, J. Sun, X. Wang, J. Sprinkle, Z. An, M. Ma, X. Cheng, T. Liu, Z. Ke, B. Zou, M. Barth, and Y .-H. Kuo, “Large Language Models for Traffic and Transportation Research: Methodologies, State of the Art, and Future Opportunities,” 3 2025. [Online]. Available: https://arxiv.org/pdf/2503.21330

    arXiv 2025

  67. [67]

    Enhancing Traffic Incident Management with Large Language Models: A Hybrid Machine Learning Approach for Severity Classification,

    A. Grigorev, K. Saleh, Y . Ou, and A.-S. Mihaita, “Enhancing Traffic Incident Management with Large Language Models: A Hybrid Machine Learning Approach for Severity Classification,” 4 2024. [Online]. Available: http://arxiv.org/abs/2403.13547

    arXiv 2024

  68. [68]

    Automating the loop in traffic incident management on highway,

    M. Cercola, N. Gatti, P. Huertas Leyva, B. Carambia, and S. Formentin SIMONEFORMENTIN, “Automating the loop in traffic incident management on highway,”Proceedings of Machine Learning Research, vol. vvv, pp. 1–13, 3 2025. [Online]. Available: https://arxiv.org/pdf/2503.12085v1

    arXiv 2025

  69. [69]

    Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM,

    T. Cai, Y . Liu, Z. Zhou, H. Ma, S. Z. Zhao, Z. Wu, and J. Ma, “Driving with Regulation: Interpretable Decision-Making for Autonomous Vehicles with Retrieval-Augmented Reasoning via LLM,” 3 2025. [Online]. Available: http://arxiv.org/abs/2410.04759

    arXiv 2025

  70. [70]

    Driving Everywhere with Large Language Model Policy Adaptation,

    B. Li, Y . Wang, J. Mao, B. Ivanovic, S. Veer, K. Leung, and M. Pavone, “Driving Everywhere with Large Language Model Policy Adaptation,”Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 14 948–14 957, 2

  71. [71]

    Available: https://arxiv.org/pdf/2402.05932

    [Online]. Available: https://arxiv.org/pdf/2402.05932

    arXiv

  72. [72]

    DelayPTC- LLM: Metro Passenger Travel Choice Prediction under Train Delays with Large Language Models,

    C. Chen, Y . He, H. Wang, J. Chen, and Q. Luo, “DelayPTC- LLM: Metro Passenger Travel Choice Prediction under Train Delays with Large Language Models,” 9 2024. [Online]. Available: https://arxiv.org/pdf/2410.00052

    arXiv 2024

  73. [73]

    ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling,

    C. Huang, Z. Tang, S. Hu, R. Jiang, X. Zheng, D. Ge, B. Wang, and Z. Wang, “ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling,”Operations Research, 5 2024. [Online]. Available: https://arxiv.org/pdf/2405.17743

    arXiv 2024

  74. [74]

    TraveLLM: Could you plan my new public transit route in face of a network disruption?

    B. Fang, Z. Yang, S. Wang, and X. Di, “TraveLLM: Could you plan my new public transit route in face of a network disruption?” 7 2024. [Online]. Available: http://arxiv.org/abs/2407.14926

    arXiv 2024

  75. [75]

    Beyond Words: Evaluating Large Language Models in Transportation Planning,

    S. Ying, Z. Li, and M. Yu, “Beyond Words: Evaluating Large Language Models in Transportation Planning,” 9 2024. [Online]. Available: https://arxiv.org/pdf/2409.14516

    arXiv 2024

  76. [76]

    TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models,

    S. Devunuri and L. Lehe, “TransitGPT: A Generative AI-based framework for interacting with GTFS data using Large Language Models,” 12 2024. [Online]. Available: https://arxiv.org/pdf/2412.06831

    arXiv 2024

  77. [77]

    Tupayachi, H

    J. Tupayachi, H. Xu, O. A. Omitaomu, M. C. Camur, A. Sharmin, and X. Li, “Towards Next-Generation Urban Decision Support Systems through AI-Powered Construction of Scientific Ontology Using Large Language Models—A Case in Optimizing Intermodal Freight Transportation,”Smart Cities 2024, Vol. 7, Pages 2392-2421, vol. 7, no. 5, pp. 2392–2421, 8 2024. [Online...

    2024

  78. [78]

    Joint estimation and prediction of city-wide delivery demand: A large language model empowered graph-based learning approach,

    T. Nie, J. He, Y . Mei, G. Qin, G. Li, J. Sun, and W. Ma, “Joint estimation and prediction of city-wide delivery demand: A large language model empowered graph-based learning approach,” Transportation Research Part E: Logistics and Transportation Review, vol. 197, p. 104075, 5 2025. [Online]. Available: https: //doi.org/10.1609/aaai.v34i04.5716

    work page doi:10.1609/aaai.v34i04.5716 2025

  79. [79]

    Fine-Tuning Pre-Trained Large Language Models for Price Prediction on Network Freight Platforms,

    P. Lu, P. Zhang, J. Wu, X. Wu, Y . Mao, and T. Liu, “Fine-Tuning Pre-Trained Large Language Models for Price Prediction on Network Freight Platforms,”Mathematics 2025, Vol. 13, Page 2504, vol. 13, no. 15, p. 2504, 8 2025. [Online]. Available: https://www.mdpi.com/2227-7390/13/15/2504/ htmhttps://www.mdpi.com/2227-7390/13/15/2504

    2025

  80. [80]

    Smart Routing for Sustainable Supply Chain Networks: An AI and Knowledge Graph Driven Approach,

    M. Felder, M. De Marchi, P. Dallasega, and E. Rauch, “Smart Routing for Sustainable Supply Chain Networks: An AI and Knowledge Graph Driven Approach,”Applied Sciences 2025, Vol. 15, Page 8001, vol. 15, no. 14, p. 8001, 7

    2025

Showing first 80 references.