LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences

2025-09-13

AI Summary

To address the challenges faced by large language models (LLMs) in natural language–driven multi-objective path planning—namely, handling high-dimensional map data, interpreting user preferences, and adapting to globally heterogeneous spatiotemporal distributions—this paper proposes the LLM-as-Parser framework. First, an LLM precisely parses natural language queries to extract and quantify multidimensional user preferences. Second, a Multi-Step Graph Search (MSGS) mechanism is designed to embed these preferences into both graph construction and iterative search. Third, the framework integrates multi-objective weighted optimization with hard-constraint satisfaction—respecting temporal windows, POI opening hours, and task dependencies—to generate personalized routes. Extensive experiments across 27 cities in 14 countries, using 1,000 real-world multi-difficulty instructions, demonstrate that our method significantly improves POI relevance and task completion rate, consistently outperforming state-of-the-art baselines.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

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

Abstract

The rise of large language models (LLMs) has made natural language-driven route planning an emerging research area that encompasses rich user objectives. Current research exhibits two distinct approaches: direct route planning using LLM-as-Agent and graph-based searching strategies. However, LLMs in the former approach struggle to handle extensive map data, while the latter shows limited capability in understanding natural language preferences. Additionally, a more critical challenge arises from the highly heterogeneous and unpredictable spatio-temporal distribution of users across the globe. In this paper, we introduce a novel LLM-Assisted route Planning (LLMAP) system that employs an LLM-as-Parser to comprehend natural language, identify tasks, and extract user preferences and recognize task dependencies, coupled with a Multi-Step Graph construction with iterative Search (MSGS) algorithm as the underlying solver for optimal route finding. Our multi-objective optimization approach adaptively tunes objective weights to maximize points of interest (POI) quality and task completion rate while minimizing route distance, subject to three key constraints: user time limits, POI opening hours, and task dependencies. We conduct extensive experiments using 1,000 routing prompts sampled with varying complexity across 14 countries and 27 cities worldwide. The results demonstrate that our approach achieves superior performance with guarantees across multiple constraints.

Problem

• Enabling natural language-driven multi-objective route planning
• Handling heterogeneous spatio-temporal user distribution constraints
• Balancing POI quality, task completion and distance optimization

Innovation

• LLM-as-Parser comprehends natural language preferences
• Multi-Step Graph construction with iterative Search
• Adaptive multi-objective optimization tuning weights