Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2511.04464 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909890639822848 |
|---|---|
| author | Braun, Carnot Jarczewski, Rafael O. Talasso, Gabriel U. Villas, Leandro A. de Souza, Allan M. |
| author_facet | Braun, Carnot Jarczewski, Rafael O. Talasso, Gabriel U. Villas, Leandro A. de Souza, Allan M. |
| contents | Traditional vehicle routing systems efficiently optimize singular metrics like time or distance, and when considering multiple metrics, they need more processes to optimize . However, they lack the capability to interpret and integrate the complex, semantic, and dynamic contexts of human drivers, such as multi-step tasks, situational constraints, or urgent needs. This paper introduces and evaluates PAVe (Personalized Agentic Vehicular Routing), a hybrid agentic assistant designed to augment classical pathfinding algorithms with contextual reasoning. Our approach employs a Large Language Model (LLM) agent that operates on a candidate set of routes generated by a multi-objective (time, CO2) Dijkstra algorithm. The agent evaluates these options against user-provided tasks, preferences, and avoidance rules by leveraging a pre-processed geospatial cache of urban Points of Interest (POIs). In a benchmark of realistic urban scenarios, PAVe successfully used complex user intent into appropriate route modifications, achieving over 88% accuracy in its initial route selections with a local model. We conclude that combining classical routing algorithms with an LLM-based semantic reasoning layer is a robust and effective approach for creating personalized, adaptive, and scalable solutions for urban mobility optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04464 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Shortest Path: Agentic Vehicular Routing with Semantic Context Braun, Carnot Jarczewski, Rafael O. Talasso, Gabriel U. Villas, Leandro A. de Souza, Allan M. Artificial Intelligence Traditional vehicle routing systems efficiently optimize singular metrics like time or distance, and when considering multiple metrics, they need more processes to optimize . However, they lack the capability to interpret and integrate the complex, semantic, and dynamic contexts of human drivers, such as multi-step tasks, situational constraints, or urgent needs. This paper introduces and evaluates PAVe (Personalized Agentic Vehicular Routing), a hybrid agentic assistant designed to augment classical pathfinding algorithms with contextual reasoning. Our approach employs a Large Language Model (LLM) agent that operates on a candidate set of routes generated by a multi-objective (time, CO2) Dijkstra algorithm. The agent evaluates these options against user-provided tasks, preferences, and avoidance rules by leveraging a pre-processed geospatial cache of urban Points of Interest (POIs). In a benchmark of realistic urban scenarios, PAVe successfully used complex user intent into appropriate route modifications, achieving over 88% accuracy in its initial route selections with a local model. We conclude that combining classical routing algorithms with an LLM-based semantic reasoning layer is a robust and effective approach for creating personalized, adaptive, and scalable solutions for urban mobility optimization. |
| title | Beyond Shortest Path: Agentic Vehicular Routing with Semantic Context |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2511.04464 |