Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discovery

TL;DR

This paper introduces WalkRAG, a spatial retrieval-augmented generation framework with a conversational interface that enhances urban discovery by recommending walkable routes based on spatial constraints and points of interest.

Contribution

The work presents a novel spatial RAG framework, WalkRAG, integrating spatial reasoning and retrieval to improve urban itinerary recommendations with interactive user engagement.

Findings

Effective combination of retrieval, spatial reasoning, and LLMs for urban discovery.

Supports user-specific spatial constraints and preferences in route planning.

Preliminary results demonstrate promising performance in urban itinerary recommendations.

Abstract

Large Language Models (LLMs) have become foundational tools in artificial intelligence, supporting a wide range of applications beyond traditional natural language processing, including urban systems and tourist recommendations. However, their tendency to hallucinate and their limitations in spatial retrieval and reasoning are well known, pointing to the need for novel solutions. Retrieval-augmented generation (RAG) has recently emerged as a promising way to enhance LLMs with accurate, domain-specific, and timely information. Spatial RAG extends this approach to tasks involving geographic understanding. In this work, we introduce WalkRAG, a spatial RAG-based framework with a conversational interface for recommending walkable urban itineraries. Users can request routes that meet specific spatial constraints and preferences while interactively retrieving information about the path and points of interest (POIs) along the way. Preliminary results show the effectiveness of combining information retrieval, spatial reasoning, and LLMs to support urban discovery.