TraveLLM: Could you plan my new public transit route in face of a network disruption?

TL;DR

TraveLLM leverages large language models to create disruption-aware public transit routing systems that process natural language queries and real-time map data, improving navigation during urban disruptions.

Contribution

This work introduces a novel LLM-based system for dynamic public transit routing that effectively incorporates real-time disruptions and user constraints, a gap in existing navigation solutions.

Findings

GPT-4 effectively generates viable travel plans during disruptions

LLMs can incorporate user preferences and real-time data

Benchmark results show LLMs outperform traditional methods in complex scenarios

Abstract

Existing navigation systems often fail during urban disruptions, struggling to incorporate real-time events and complex user constraints, such as avoiding specific areas. We address this gap with TraveLLM, a system using Large Language Models (LLMs) for disruption-aware public transit routing. We leverage LLMs' reasoning capabilities to directly process multimodal user queries combining natural language requests (origin, destination, preferences, disruption info) with map data (e.g., subway, bus, bike-share). To evaluate this approach, we design challenging test scenarios reflecting real-world disruptions like weather events, emergencies, and dynamic service availability. We benchmark the performance of state-of-the-art LLMs, including GPT-4, Claude 3, and Gemini, on generating accurate travel plans. Our experiments demonstrate that LLMs, notably GPT-4, can effectively generate viable and context-aware navigation plans under these demanding conditions. These findings suggest a promising direction for using LLMs to build more flexible and intelligent navigation systems capable of handling dynamic disruptions and diverse user needs.