GeoZero: Incentivizing Reasoning from Scratch on Geospatial Scenes

TL;DR

GeoZero introduces a novel framework for geospatial reasoning in multimodal large language models that eliminates the need for chain-of-thought supervision, using datasets and reinforcement learning to enhance reasoning without human bias.

Contribution

It presents GeoZero, a new approach that enables reasoning without predefined CoT data, utilizing datasets and a novel reinforcement learning method to improve geospatial understanding.

Findings

Outperforms existing state-of-the-art methods on remote sensing benchmarks.

Fosters universal emergent reasoning capabilities across diverse geospatial tasks.

Demonstrates effective reasoning without human-annotated chain-of-thought data.

Abstract

Multimodal large language models (MLLMs) have undergone rapid development in advancing geospatial scene understanding. Recent studies have sought to enhance the reasoning capabilities of remote sensing MLLMs, typically through cold-start training with elaborately curated chain-of-thought (CoT) data. However, this approach not only incurs substantial annotation costs but also introduces human biases that may limit the diversity of model reasoning. To address these challenges, we propose GeoZero, a framework that enables MLLMs to perform geospatial reasoning without any predefined CoT supervision. Specifically, we construct two datasets, GeoZero-Instruct and GeoZero-Hard. GeoZero-Instruct allows the model to acquire preliminary geospatial knowledge through supervised fine-tuning, while GeoZero-Hard stimulates deep reasoning during the subsequent reinforcement learning stage. Furthermore, we introduce Answer-Anchored Group Relative Policy Optimization (A$^2$GRPO), where the reasoning process is regularized by the model's own answers, encouraging diverse yet accurate thinking. Extensive experiments on multiple remote sensing vision-language benchmarks demonstrate that GeoZero not only surpasses existing state-of-the-art methods but also fosters universal emergent reasoning capabilities across diverse geospatial tasks. Code, data, and models are available at https://github.com/MiliLab/GeoZero.