Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discovery
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909943538384896 |
|---|---|
| author | Amendola, Maddalena Pugliese, Chiara Perego, Raffaele Renso, Chiara |
| author_facet | Amendola, Maddalena Pugliese, Chiara Perego, Raffaele Renso, Chiara |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04790 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discovery Amendola, Maddalena Pugliese, Chiara Perego, Raffaele Renso, Chiara Information Retrieval 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. |
| title | Spatially-Enhanced Retrieval-Augmented Generation for Walkability and Urban Discovery |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2512.04790 |