Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. While raw geospatial imagery is abundant, the amount of task-direct supervision falls far behind that of common domains. In this work, we validate an important conclusion: indirect verifiable rewards, derived from seemingly unrelated metadata, are sufficient to induce sophisticated and generalizable geospatial reasoning across a wide range of downstream tasks (25+). We present Geo-R1 as one empirical instantiation of this paradigm. Rather than relying on limited task-specific annotations (i.e., direct rewards), Geo-R1 utilizes scalable, verifiable indirect proxy rewards based on cross-view alignment with metadata (geolocation information) to drive reinforcement learning at scale. Such indirect rewards successfully motivate the model to discover and internalize zero-shot geospatial reasoning across diverse tasks, achieving extraordinary zero-shot transfer on out-of-distribution benchmarks and even surpassing fully supervised specialists on certain benchmarks. These findings indicate that optimizing for indirect verifiable rewards may provide a scalable pathway to unlock generalized reasoning capabilities in rare domains with massive unlabeled data archives. Our code is availavle at: https://github.com/miniHuiHui/Geo-R1.
@article{arxiv.2510.00072,
title = {Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards},
author = {Chenhui Xu and Fuxun Yu and Michael J. Bianco and Jacob Kovarskiy and Raphael Tang and Qi Zhang and Zirui Xu and Will LeVine and Brandon Dubbs and Heming Liao and Cassandra Burgess and Suvam Bag and Jay Patravali and Rupanjali Kukal and Mikael Figueroa and Rishi Madhok and Nikolaos Karianakis and Jinjun Xiong},
journal= {arXiv preprint arXiv:2510.00072},
year = {2026}
}