GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization

TL;DR

GeoVista is a novel agentic model that combines visual reasoning and web search to improve geolocalization accuracy, supported by a new benchmark GeoBench with diverse high-resolution imagery.

Contribution

The paper introduces GeoVista, a new agentic model with integrated tool use for geolocalization, and curates GeoBench, a comprehensive benchmark for evaluating such models.

Findings

GeoVista outperforms other open-source models on GeoBench.

GeoVista achieves comparable results to closed-source models like Gemini-2.5-flash and GPT-5.

The hierarchical reward improves geolocalization performance.

Abstract

Current research on agentic visual reasoning enables deep multimodal understanding but primarily focuses on image manipulation tools, leaving a gap toward more general-purpose agentic models. In this work, we revisit the geolocalization task, which requires not only nuanced visual grounding but also web search to confirm or refine hypotheses during reasoning. Since existing geolocalization benchmarks fail to meet the need for high-resolution imagery and the localization challenge for deep agentic reasoning, we curate GeoBench, a benchmark that includes photos and panoramas from around the world, along with a subset of satellite images of different cities to rigorously evaluate the geolocalization ability of agentic models. We also 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 web information. We develop a complete training pipeline for it, including a cold-start supervised fine-tuning (SFT) stage to learn reasoning patterns and tool-use priors, followed by a reinforcement learning (RL) stage to further enhance reasoning ability. We adopt a hierarchical reward to leverage multi-level geographical information and improve overall geolocalization performance. Experimental results show that GeoVista surpasses other open-source agentic models on the geolocalization task greatly and achieves performance comparable to closed-source models such as Gemini-2.5-flash and GPT-5 on most metrics.