PathGPT: Leveraging Large Language Models for Personalized Route Generation

2025-04-08

AI Summary

Existing personalized route recommendation (PRR) models suffer from poor generalizability and high adaptation costs across diverse scenarios, necessitating task-specific retraining. Method: We propose the first unified PRR framework based on large language models (LLMs), enabling zero-shot transfer to unseen scenarios without fine-tuning. Our approach introduces an end-to-end LLM-based path generation paradigm; designs a RAG-inspired mechanism for dynamic injection of geographic and user-contextual knowledge; and incorporates a trajectory semantic prompting module coupled with geographic encoding to support natural-language constraints (e.g., “avoid highways” or “pass by a café”). Results: Evaluated on multiple real-world trajectory datasets, our framework significantly improves recommendation accuracy and personalized satisfaction, overcoming key limitations of conventional supervised trajectory models—namely, weak generalization and cumbersome deployment.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The proliferation of GPS enabled devices has led to the accumulation of a substantial corpus of historical trajectory data. By leveraging these data for training machine learning models,researchers have devised novel data-driven methodologies that address the personalized route recommendation (PRR) problem. In contrast to conventional algorithms such as Dijkstra shortest path algorithm,these novel algorithms possess the capacity to discern and learn patterns within the data,thereby facilitating the generation of more personalized paths. However,once these models have been trained,their application is constrained to the generation of routes that align with their training patterns. This limitation renders them less adaptable to novel scenarios and the deployment of multiple machine learning models might be necessary to address new possible scenarios,which can be costly as each model must be trained separately. Inspired by recent advances in the field of Large Language Models (LLMs),we leveraged their natural language understanding capabilities to develop a unified model to solve the PRR problem while being seamlessly adaptable to new scenarios without additional training. To accomplish this,we combined the extensive knowledge LLMs acquired during training with further access to external hand-crafted context information,similar to RAG (Retrieved Augmented Generation) systems,to enhance their ability to generate paths according to user-defined requirements. Extensive experiments on different datasets show a considerable uplift in LLM performance on the PRR problem.

Problem

• Personalized route recommendation using historical trajectory data
• Overcoming limitations of conventional algorithms with LLMs
• Adapting to new scenarios without additional training

Innovation

• Leveraging LLMs for personalized route generation
• Combining LLMs with external context information
• Adapting to new scenarios without additional training