# Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning

arXiv: https://arxiv.org/abs/2603.10463 · HTML: https://mlsanity.com/paper/2603.10463/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 28 of 28)

- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization](https://mlsanity.com/paper/2204.00097/) (2022)
- [PlaNet - Photo Geolocation with Convolutional Neural Networks](https://mlsanity.com/paper/1602.05314/) (2016)
- [Revisiting IM2GPS in the Deep Learning Era](https://mlsanity.com/paper/1705.04838/) (2017)
- [Cross-view Geo-localization via Learning Disentangled Geometric Layout Correspondence](https://mlsanity.com/paper/2212.04074/) (2022)
- [CPlaNet: Enhancing Image Geolocalization by Combinatorial Partitioning of Maps](https://mlsanity.com/paper/1808.02130/) (2018)
- [DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model](https://mlsanity.com/paper/2304.11582/) (2023)
- [Where in the World is this Image? Transformer-based Geo-localization in the Wild](https://mlsanity.com/paper/2204.13861/) (2022)
- [ControlTraj: Controllable Trajectory Generation with Topology-Constrained Diffusion Model](https://mlsanity.com/paper/2404.15380/) (2024)
- [The StreetLearn Environment and Dataset](https://mlsanity.com/paper/1903.01292/) (2019)
- [Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization](https://mlsanity.com/paper/2302.00275/) (2023)
- [OpenStreetView-5M: The Many Roads to Global Visual Geolocation](https://mlsanity.com/paper/2404.18873/) (2024)
- [Interpretable Semantic Photo Geolocation](https://mlsanity.com/paper/2104.14995/) (2021)
- [Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation](https://mlsanity.com/paper/2403.19584/) (2024)
- [The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes](https://mlsanity.com/paper/2601.11659/) (2026)
- [Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework](https://mlsanity.com/paper/2502.13759/) (2025)
- [MLPST: MLP is All You Need for Spatio-Temporal Prediction](https://mlsanity.com/paper/2309.13363/) (2023)
- [PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction](https://mlsanity.com/paper/2309.09500/) (2023)
- [AutoSTL: Automated Spatio-Temporal Multi-Task Learning](https://mlsanity.com/paper/2304.09174/) (2023)

## Built on by (most cited first, 3 of 3)

- [Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition](https://mlsanity.com/paper/2604.05523/) (2026)
- [A3: Towards Advertising Aesthetic Assessment](https://mlsanity.com/paper/2603.24037/) (2026)
- [GeoRouter: Dynamic Paradigm Routing for Worldwide Image Geolocalization](https://mlsanity.com/paper/2603.24376/) (2026)

## Abstract (arXiv)

Geolocation, the task of identifying the geographic location of an image, requires abundant world knowledge and complex reasoning abilities. Though advanced large multimodal models (LMMs) have shown superior aforementioned capabilities, their performance on the geolocation task remains unexplored. To this end, we introduce WanderBench, the first open access global geolocation benchmark designed for actionable geolocation reasoning in embodied scenarios. WanderBench contains over 32K panoramas across six continents, organized as navigable graphs that enable physical actions such as rotation and movement, transforming geolocation from static recognition into interactive exploration. Building on this foundation, we propose GeoAoT (Action of Thought), a underlineGeolocation framework with underlineAction of underlineThough, which couples reasoning with embodied actions. Instead of generating textual reasoning chains, GeoAoT produces actionable plans such as, approaching landmarks or adjusting viewpoints, to actively reduce uncertainty. We further establish an evaluation protocol that jointly measures geolocation accuracy and difficulty-aware geolocation questioning ability. Experiments on 19 large multimodal models show that GeoAoT achieves superior fine-grained localization and stronger generalization in dynamic environments. WanderBench and GeoAoT define a new paradigm for actionable, reasoning driven geolocation in embodied visual understanding.