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

• URL: http://arxiv.org/abs/2603.10463v1
• Date: Wed, 11 Mar 2026 06:24:10 GMT
• Title: Learning to Wander: Improving the Global Image Geolocation Ability of LMMs via Actionable Reasoning
• Abstract summary: We introduce textbfWanderBench, the first open access global geolocation benchmark for actionable geolocation reasoning in embodied scenarios.<n>We propose textbfGeoAoT (Action of Thought), a underlineGeolocation framework with underlineAction of underlineThough, which couples reasoning with embodied actions.<n>Experiments on 19 large multimodal models show that GeoAoT achieves superior fine-grained localization and stronger generalization in dynamic environments.
• Score: 72.13218601075958
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 \textbf{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 \textbf{GeoAoT} (Action of Thought), a \underline{Geo}location framework with \underline{A}ction of \underline{T}hough, 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.

Related papers

• ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language Models [17.86934121595618]
  ERGeoBench is a diagnostic benchmark for vision-driven embodied geo-localization.<n> benchmark contains 2,207 globally distributed street-view panoramas.<n> ERGeoBench provides a unified framework for diagnosing and advancing human-like embodied geo-localization.
  arXiv  Detail & Related papers  (2026-05-29T12:49:17Z)
• GeoAgent: Learning to Geolocate Everywhere with Reinforced Geographic Characteristics [91.17301794848025]
  This paper presents GeoAgent, a model capable of reasoning closely with humans and deriving fine-grained address conclusions.<n>Previous RL-based methods have achieved breakthroughs in performance and interpretability but still remain concerns because of their reliance on AI-generated chain-of-thought (CoT) data and training strategies.
  arXiv  Detail & Related papers  (2026-02-13T04:48:05Z)
• Vision-Language Reasoning for Geolocalization: A Reinforcement Learning Approach [41.001581773172695]
  We present Geo-R, a retrieval-free framework that uncovers structured reasoning paths from existing ground-truth coordinates.<n>We propose the Chain of Region, a rule-based hierarchical reasoning paradigm that generates precise, interpretable supervision.<n>Our approach bridges structured geographic reasoning with direct spatial supervision, yielding improved localization accuracy, stronger generalization, and more transparent inference.
  arXiv  Detail & Related papers  (2026-01-01T16:51:41Z)
• GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization [53.080882980294795]
  Current research on agentic visual reasoning enables deep multimodal understanding but primarily focuses on image manipulation tools.<n>In this work, we revisit the geolocalization task, which requires not only nuanced visual grounding but also web search to confirm or refine hypotheses.<n>Since existing geolocalization benchmarks fail to meet the need for high-resolution imagery and the localization challenge for deep agentic reasoning, we curate GeoBench.<n>We propose GeoVista, an agentic model that seamlessly integrates tool invocation within the reasoning loop, including an image-zoom-in tool to magnify regions of interest and a web-search tool to retrieve related
  arXiv  Detail & Related papers  (2025-11-19T18:59:22Z)
• Towards Interpretable Geo-localization: a Concept-Aware Global Image-GPS Alignment Framework [9.31168320050859]
  Geo-localization involves determining the exact geographic location of images captured globally.<n>Current concept-based interpretability methods fail to align effectively with Geo-alignment image-location embedding objectives.<n>To our knowledge, this is the first work to introduce interpretability into geo-localization.
  arXiv  Detail & Related papers  (2025-09-02T03:07:26Z)
• Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework [59.42946541163632]
  We introduce a comprehensive geolocation framework with three key components.<n>GeoComp, a large-scale dataset; GeoCoT, a novel reasoning method; and GeoEval, an evaluation metric.<n>We demonstrate that GeoCoT significantly boosts geolocation accuracy by up to 25% while enhancing interpretability.
  arXiv  Detail & Related papers  (2025-02-19T14:21:25Z)
• GaGA: Towards Interactive Global Geolocation Assistant [20.342366228855735]
  GaGA is an interactive global geolocation assistant built upon the flourishing large vision-language models (LVLMs)<n>It uncovers geographical clues within images and combines them with the extensive world knowledge embedded in LVLMs to determine the geolocations.<n>GaGA achieves state-of-the-art performance on the GWS15k dataset, improving accuracy by 4.57% at the country level and 2.92% at the city level.
  arXiv  Detail & Related papers  (2024-12-12T03:39:44Z)
• GOMAA-Geo: GOal Modality Agnostic Active Geo-localization [49.599465495973654]
  We consider the task of active geo-localization (AGL) in which an agent uses a sequence of visual cues observed during aerial navigation to find a target specified through multiple possible modalities. GOMAA-Geo is a goal modality active geo-localization agent for zero-shot generalization between different goal modalities.
  arXiv  Detail & Related papers  (2024-06-04T02:59:36Z)
• GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization [61.10806364001535]
  Worldwide Geo-localization aims to pinpoint the precise location of images taken anywhere on Earth. Existing approaches divide the globe into discrete geographic cells, transforming the problem into a classification task. We propose GeoCLIP, a novel CLIP-inspired Image-to-GPS retrieval approach that enforces alignment between the image and its corresponding GPS locations.
  arXiv  Detail & Related papers  (2023-09-27T20:54:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.