Lune

ACL Findings2026

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

Jian Cui, Zhiyuan Ren, Desheng Weng, Yongqi Zhao, Gong Wenbin, Yu Lei, Zhenning Dong

Abstract

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 distancedeviation-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.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on3

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Rethinking Visual Geo-localization for Large-Scale ApplicationsGabriele Moreno Berton, Carlo Masone, Barbara CaputoCVPR 2022 · 235 citations
  3. G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality ModelsPengyue Jia, Yiding Liu, Xiaopeng Li, Xiangyu Zhao et al.NeurIPS 2024 · 60 citations

Related papers

  1. Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement LearningMing Chen, Sheng Tang, Rong-Xi Tan, Ziniu Li et al.ICML 2026 · 2 citations
  2. Vision-Language Reasoning for Geolocalization: A Reinforcement Learning ApproachBiao Wu, Meng Fang, Ling Chen, Ke Xu et al.AAAI 2026 · 2 citations
  3. CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric RewardYandong Guan, Xilin Wang, Ximing Xing, Jing Zhang et al.NeurIPS 2025 · 64 citations
  4. GeoAgent: To Empower LLMs using Geospatial Tools for Address StandardizationChenghua Huang, Shisong Chen, Zhixu Li, Jianfeng Qu et al.ACL Findings 2024 · 24 citations
  5. GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic CharacteristicsModi Jin, Yiming Zhang, Boyuan Sun, Dingwen Zhang et al.CVPR 2026 · 7 citations
Dusk over the sea between two cliffs drawn in fine vertical lines