CoChat
Sign Up
Cited by 4Traffic Prediction and Management TechniquesTransportation Planning and OptimizationUrban Design and Spatial Analysis

PathGen-LLM: A Large Language Model for Dynamic Path Generation in Complex Transportation Networks

Open access
Li, Xun, Xian, Kai, Wen, Huimin, Bai, Shengguang, Xu, Han, Yu, Yun·2025·Mathematics
DOI 10.3390/math13193073
Open this paper in CoChat — free accountOpen PDF

Abstract

Dynamic path generation in complex transportation networks is essential for intelligent transportation systems. Traditional methods, such as shortest path algorithms or heuristic-based models, often fail to capture real-world travel behaviors due to their reliance on simplified assumptions and limited ability to handle long-range dependencies or non-linear patterns. To address these limitations, we propose PathGen-LLM, a large language model (LLM) designed to learn spatial–temporal patterns from historical paths without requiring handcrafted features or graph-specific architectures. Exploiting the structural similarity between path sequences and natural language, PathGen-LLM converts spatiotemporal trajectories into text-formatted token sequences by encoding node IDs and timestamps. This enables the model to learn global dependencies and semantic relationships through self-supervised pretraining. The model integrates a hierarchical Transformer architecture with dynamic constraint decoding, which synchronizes spatial node transitions with temporal timestamps to ensure physically valid paths in large-scale road networks. Experimental results on real-world urban datasets demonstrate that PathGen-LLM outperforms baseline methods, particularly in long-distance path generation. By bridging sequence modeling and complex network analysis, PathGen-LLM offers a novel framework for intelligent transportation systems, highlighting the potential of LLMs to address challenges in large-scale, real-time network tasks.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/math13193073

Cites

30 of 30 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The results confirm the prediction of IIT regarding the causal decomposability of LLMs.

    “Thus, the results confirm the prediction of IIT regarding the causal decomposability of LLMs [12] and ground it empirically via behaviorally interpretable metrics (e.g., perplexity [15]).”

    From Why large language models cannot possess consciousness: an integrated information theory perspective (2025) · cites this paper as [15]

    The Introduction and §5.8 discuss LLM path generation and scaling, not integrated information theory (IIT) or causal decomposability. A search for those terms found no passage in our copy reporting or testing the claimed IIT prediction; §5.9.2 instead discusses interpretability as an open challenge. (LLM, conf=0.77)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 14

  1. Tyagi, N.; Singh, J.; Singh, S. A Review of Routing Algorithms for Intelligent Route Planning and Path Optimization in Road Navigation. In Proceedings of the Recent Trends in Product Design and Intelligent Manufacturing Systems;
  2. Koenig, S.; Likhachev, M. D* Lite. In Proceedings of the 18th National Conference on Artificial Intelligence, Edmonton, AB, Canada, 28 July-1 August 2002; pp. 182-188.
  3. Wu, H.; Chen, Z.; Sun, W.; Zheng, B.; Wang, W. Modeling trajectories with recurrent neural networks. In Proceedings of the 26th International Joint Conference on Artificial Intelligence, Melbourne, Australia, 19-25 August 2017; IJCAI'17, pp. 3083-3090.
  4. Jain, J.; Bagadia, V.; Manchanda, S.; Ranu, S. NEUROMLR: Robust & reliable route recommendation on road networks. In Proceedings of the 35th International Conference on Neural Information Processing Systems, Red Hook, NY, USA, 6-14 December 2021; NIPS '21.
  5. Wei, J.; Tay, Y.; Bommasani, R.; Raffel, C.; Zoph, B.; Borgeaud, S.; Yogatama, D.; Bosma, M.; Zhou, D.; Metzler, D.; et al. Emergent Abilities of Large Language Models. Trans. Mach. Learn. Res. 2022. [CrossRef] · DOI · Paper page
  6. Cao, J.; Zheng, T.; Guo, Q.; Wang, Y.; Dai, J.; Liu, S.; Yang, J.; Song, J.; Song, M. Holistic semantic representation for navigational trajectory generation. In Proceedings of the Thirty-Ninth AAAI Conference on Artificial Intelligence and Thirty-Seventh Conference on Innovative Applications of Artificial Intelligence and Fifteenth Symposium on Educational Advances in Artificial Intelligence, Philadelphia, PA, USA, 25 February-4 March 2025; AAAI'25/IAAI'25/EAAI'25. [CrossRef] · DOI
  7. Wang, D.; Zhang, J.; Cao, W.; Li, J.; Zheng, Y. When will you arrive? estimating travel time based on deep neural networks. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, LA, USA, 2-7 February 2018; AAAI'18/IAAI'18/EAAI'18.
  8. Ren, Y.; Chen, Y.; Liu, S.; Wang, B.; Yu, H.; Cui, Z. TPLLM: A Traffic Prediction Framework Based on Pretrained Large Language Models. arXiv 2024, arXiv:cs.LG/2403.02221. [CrossRef] · DOI
  9. Huang, Z.; Shi, G.; Sukhatme, G.S. Can Large Language Models Solve Robot Routing? arXiv 2024, arXiv:cs.CL/2403.10795.
  10. Wang, L.; Duan, P.; He, Z.; Lyu, C.; Chen, X.; Zheng, N.; Yao, L.; Ma, Z. AI-Driven Day-to-Day Route Choice. arXiv 2024, arXiv:cs.LG/2412.03338.
  11. Marcelyn, S.C.; Gao, Y.; Zhang, Y.; Gao, X.; Chen, G. PathGPT: Leveraging Large Language Models for Personalized Route Generation. arXiv 2025, arXiv:cs.IR/2504.05846. [CrossRef] · DOI
  12. Shlegeris, B.; Roger, F.; Chan, L.; McLean, E. Language Models Are Better Than Humans at Next-token Prediction. Trans. Mach. Learn. Res. 2024. [CrossRef] · DOI
  13. Brown, T.B.; Mann, B.; Ryder, N.; Subbiah, M.; Kaplan, J.; Dhariwal, P.; Neelakantan, A.; Shyam, P.; Sastry, G.; Askell, A.; et al. Language models are few-shot learners. In Proceedings of the 34th International Conference on Neural Information Processing Systems, Red Hook, NY, USA, 6-12 December 2020; NIPS '20.
  14. Singh, C.; Inala, J.P.; Galley, M.; Caruana, R.; Gao, J. Rethinking Interpretability in the Era of Large Language Models. arXiv 2024, arXiv:cs.CL/2402.01761. [CrossRef · DOI · Paper page

Cited by

Sorted by citations

Authors
Li, X., Xian, K., Wen, H., Bai, S., Xu, H., & Yu, Y.
Affiliations
  • Beijing Jiaotong University (CN)
  • Beijing Transport Institute, Beijing 100161, China
  • Cornell University (US)
Corresponding author
Wen, Huimin
ORCID
Venue
Mathematics
Publisher
MDPI AG
Published
2025-09-24
Volume
13
Issue
19
Pages
3073
ISSN
2227-7390 (ISSN-L)
DOI
10.3390/math13193073
OpenAlex
W4414473092
Cited by
4
References
30
Citations by year
2026: 2 · 2025: 2
FWCI
1.67
Type
journal article
Language
en
Open access
Licence
Locations
  • Mathematics (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
National Natural Science Foundation of China (72288101)
Topics
  • Physical Sciences › Engineering › Building and Construction › Traffic Prediction and Management Techniques
  • Social Sciences › Transportation › Transportation Planning and Optimization
  • Physical Sciences › Engineering › Building and Construction › Urban Design and Spatial Analysis
Keywords
large language models, transportation networks, spatio-temporal trajectories, hierarchical transformer, self-supervised pre-training, intelligent transportation systems, urban road networks, travel behavior modeling

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review