VAMOS! Agent: Semantic Context-Aware Vehicle Route Planning with LLM Agents

• Carnot Braun UNICAMP https://orcid.org/0009-0006-3691-7584
• Daniel L. Guidoni UFOP https://orcid.org/0000-0002-1953-9132
• Eduardo Cerqueira UFPA https://orcid.org/0000-0003-2162-6523
• Joahannes B. D. da Costa UNIFESP https://orcid.org/0000-0001-9973-2479
• Leandro Villas UNICAMP https://orcid.org/0000-0002-3372-3366
• Allan M. de Souza UNICAMP https://orcid.org/0000-0002-5518-8392

DOI: https://doi.org/10.5753/sbrc.2026.19806

Abstract

Traditional navigation systems prioritize metric efficiency, such as time or distance, but often fail to interpret complex, context-dependent human intentions. Although Large Language Models (LLMs) demonstrate the potential to bridge this semantic gap, their direct integration into Intelligent Transportation Systems (ITS) faces critical barriers regarding scalability, latency, and connectivity dependence. To overcome these challenges, this work presents VAMOS(Vehicular Agent for Multi-objective Optimization and Semantics), a hybrid agent designed for efficient onboard operation. VAMOS decouples semantic reasoning from spatial optimization, combining local Small Language Models (SLMs) for intent interpretation with classic graph algorithms for route execution. Experimental evaluation across three urban scenarios demonstrates that VAMOS achieves accuracy and completeness exceeding 91% using compact models. Furthermore, the results highlight a favorable trade-off: although massive models show a marginal quality gain (3%), VAMOS offers a significant reduction in computational and communication overhead, validating the feasibility of semantically aware navigation assistants.

References

Barbon, R. S., Madeira, E. R., and Akabane, A. T. (2025). A two-context-aware approach for navigation: A case study for vehicular route recommendation. Ad Hoc Networks, 166:103655.

Benmessaoud, Y., Cherrat, L., and Ezziyyani, M. (2023). Real-time self-adaptive traffic management system for optimal vehicular navigation in modern cities. Computers, 12(4):80.

Braun, C., Jarczewski, R. O., Talasso, G. U., Villas, L. A., and de Souza, A. M. (2025). Beyond shortest path: Agentic vehicular routing with semantic context.

Chen, A., Ge, X., Fu, Z., Xiao, Y., and Chen, J. (2024a). Travelagent: An ai assistant for personalized travel planning. arXiv preprint arXiv:2409.08069.

Chen, R., Song, W., Zu, W., Dong, Z., Guo, Z., Sun, F., Tian, Z., and Wang, J. (2024b). An llm-driven framework for multiple-vehicle dispatching and navigation in smart city landscapes. In 2024 IEEE International Conference on Robotics and Automation (ICRA), pages 2147–2153.

de Souza, A. M., Braun, T., Botega, L. C., Cabral, R., Garcia, I. C., and Villas, L. A. (2019). Better safe than sorry: a vehicular traffic re-routing based on traffic conditions and public safety issues. Journal of Internet Services and Applications, 10(1):17.

De Souza, A. M., Brennand, C. A., Yokoyama, R. S., Donato, E. A., Madeira, E. R., and Villas, L. A. (2017). Traffic management systems: A classification, review, challenges, and future perspectives. International Journal of Distributed Sensor Networks, 13(4):1550147716683612.

de Souza, A. M., Oliveira, H. F., Zhao, Z., Braun, T., Loureiro, A. A., and Villas, L. A. (2022). Enhancing sensing and decision-making of automated driving systems with multi-access edge computing and machine learning. IEEE Intelligent Transportation Systems Magazine, 14(1):44–56.

Gong, L., Lin, Y., Zhang, X., Lu, Y., Han, X., Liu, Y., Guo, S., Lin, Y., and Wan, H. (2024). Mobility-llm: Learning visiting intentions and travel preference from human mobility data with large language models. Advances in Neural Information Processing Systems, 37:36185–36217.

Huang, Z., Shi, G., and Sukhatme, G. S. (2024). From words to routes: Applying large language models to vehicle routing. CoRR, abs/2403.10795.

Irugalbandara, C., Mahendra, A., Daynauth, R., Arachchige, T. K., Dantanarayana, J., Flautner, K., Tang, L., Kang, Y., and Mars, J. (2024). Scaling down to scale up: A cost-benefit analysis of replacing openai’s llm with open source slms in production. In 2024 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pages 280–291.

Jiang, K., Cai, X., Cui, Z., Li, A., Ren, Y., Yu, H., Yang, H., Fu, D., Wen, L., and Cai, P. (2025). Koma: Knowledge-driven multi-agent framework for autonomous driving with large language models. IEEE Transactions on Intelligent Vehicles, 10(10):4655–4668.

Luca, M., Barlacchi, G., Lepri, B., and Pappalardo, L. (2021). A survey on deep learning for human mobility.

Ning, Y. and Liu, H. (2024). Urbankgent: A unified large language model agent framework for urban knowledge graph construction. Advances in Neural Information Processing Systems, 37:123127–123154.

Paiva, S., Ahad, M. A., Tripathi, G., Feroz, N., and Casalino, G. (2021). Enabling technologies for urban smart mobility: Recent trends, opportunities and challenges. Sensors, 21(6):2143.

Qin, Z., Zhang, P., Wang, L., and Ma, Z. (2025). Lingotrip: Spatiotemporal context prompt driven large language model for individual trip prediction. Journal of Public Transportation, 27:100117.

Wang, J., Jiang, R., Yang, C., Wu, Z., Onizuka, M., Shibasaki, R., Koshizuka, N., and Xiao, C. (2024). Large language models as urban residents: An llm agent framework for personal mobility generation. In Globerson, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J., and Zhang, C., editors, Advances in Neural Information Processing Systems, volume 37, pages 124547–124574. Curran Associates, Inc.

Wang, R., Zhou, M., Gao, K., Alabdulwahab, A., and Rawa, M. J. (2022). Personalized route planning system based on driver preference. Sensors, 22(1).

Wang, X., Fang, M., Zeng, Z., and Cheng, T. (2023). Where would I go next? large language models as human mobility predictors. CoRR, abs/2308.15197.

Wei, J., Wang, X., Schuurmans, D., Bosma, M., Xia, F., Chi, E., Le, Q. V., Zhou, D., et al. (2022). Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, 35:24824–24837.

Wu, Z., Peng, R., Han, X., Zheng, S., Zhang, Y., and Xiao, C. (2023). Smart agent-based modeling: On the use of large language models in computer simulations.

Xi, Z., Chen, W., Guo, X., He, W., Ding, Y., Hong, B., Zhang, M., Wang, J., Jin, S., Zhou, E., Zheng, R., Fan, X., Wang, X., Xiong, L., Zhou, Y., Wang, W., Jiang, C., Zou, Y., Liu, X., Yin, Z., Dou, S., Weng, R., Cheng, W., Zhang, Q., Qin, W., Zheng, Y., Qiu, X., Huang, X., and Gui, T. (2023). The rise and potential of large language model based agents: A survey.

Yang, K., Guo, Z., Lin, G., Dong, H., Huang, Z., Wu, Y., Zuo, D., Peng, J., Zhong, Z., WANG, X., Guo, Q., Jia, X., Yan, J., and Lin, D. (2025). Trajectory-LLM: A language-based data generator for trajectory prediction in autonomous driving. In The Thirteenth International Conference on Learning Representations.

Zhang, S., Li, J., Shi, L., Ding, M., Nguyen, D. C., Tan, W., Weng, J., and Han, Z. (2024a). Federated learning in intelligent transportation systems: Recent applications and open problems. IEEE Transactions on Intelligent Transportation Systems, 25(5):3259–3285.

Zhang, S., Luo, Z., Yang, L., Teng, F., and Li, T. (2024b). A survey of route recommendations: Methods, applications, and opportunities.

Zheng, K., Zheng, Q., Chatzimisios, P., Xiang, W., and Zhou, Y. (2015). Vehicular networking: A survey and tutorial on requirements, architectures, challenges, standards and solutions. IEEE Communications Surveys & Tutorials, 17(4):2377–2396.

Zhou, Y., Lai, S., Han, J., and Liu, H. (2025). An llm-powered cooperative framework for large-scale multi-vehicle navigation.

Zhou, Z., Lin, Y., Jin, D., and Li, Y. (2024). Large language model for participatory urban planning.