Beyond Shortest Path: Agentic Vehicular Routing with Semantic Context

TL;DR

This paper presents PAVe, a hybrid routing system that combines classical algorithms with semantic reasoning via an LLM to incorporate complex user preferences and contextual information for personalized urban vehicle routing.

Contribution

It introduces PAVe, a novel approach integrating LLM-based semantic reasoning with traditional routing algorithms for enhanced personalized vehicular navigation.

Findings

Achieved over 88% accuracy in route selection in urban scenarios.

Effectively incorporated complex user preferences and contextual information.

Demonstrated robustness and scalability of the hybrid approach.

Abstract

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.