ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cui, Jian, Ren, Zhiyuan, Weng, Desheng, Zhao, Yongqi, Wenbin, Gong, Lei, Yu, Dong, Zhenning
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917431012753408
author Cui, Jian
Ren, Zhiyuan
Weng, Desheng
Zhao, Yongqi
Wenbin, Gong
Lei, Yu
Dong, Zhenning
author_facet Cui, Jian
Ren, Zhiyuan
Weng, Desheng
Zhao, Yongqi
Wenbin, Gong
Lei, Yu
Dong, Zhenning
contents This paper proposes ReaGeo, an end-to-end geocoding framework based on large language models, designed to overcome the limitations of traditional multi-stage approaches that rely on text or vector similarity retrieval over geographic databases, including workflow complexity, error propagation, and heavy dependence on structured geographic knowledge bases. The method converts geographic coordinates into geohash sequences, reformulating the coordinate prediction task as a text generation problem, and introduces a Chain-of-Thought mechanism to enhance the model's reasoning over spatial relationships. Furthermore, reinforcement learning with a distance-deviation-based reward is applied to optimize the generation accuracy. Comprehensive experiments show that ReaGeo can accurately handle explicit address queries in single-point predictions and effectively resolve vague relative location queries. In addition, the model demonstrates strong predictive capability for non-point geometric regions, highlighting its versatility and generalization ability in geocoding tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_21357
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs
Cui, Jian
Ren, Zhiyuan
Weng, Desheng
Zhao, Yongqi
Wenbin, Gong
Lei, Yu
Dong, Zhenning
Artificial Intelligence
Computation and Language
I.2.7; I.2.6; H.2.8
This paper proposes ReaGeo, an end-to-end geocoding framework based on large language models, designed to overcome the limitations of traditional multi-stage approaches that rely on text or vector similarity retrieval over geographic databases, including workflow complexity, error propagation, and heavy dependence on structured geographic knowledge bases. The method converts geographic coordinates into geohash sequences, reformulating the coordinate prediction task as a text generation problem, and introduces a Chain-of-Thought mechanism to enhance the model's reasoning over spatial relationships. Furthermore, reinforcement learning with a distance-deviation-based reward is applied to optimize the generation accuracy. Comprehensive experiments show that ReaGeo can accurately handle explicit address queries in single-point predictions and effectively resolve vague relative location queries. In addition, the model demonstrates strong predictive capability for non-point geometric regions, highlighting its versatility and generalization ability in geocoding tasks.
title ReaGeo: Reasoning-Enhanced End-to-End Geocoding with LLMs
topic Artificial Intelligence
Computation and Language
I.2.7; I.2.6; H.2.8
url https://arxiv.org/abs/2604.21357