GeoX：通过自我对战和可验证奖励掌握地理空间推理
GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards
AI总结：
本文提出GeoX框架，通过自我对战和可验证奖励解决图像 grounded 的复杂空间问题，无需大规模人工标注数据，提升了基础视觉语言模型在地理空间理解上的性能。
摘要：
地理空间推理需要解决图像 grounded 的问题，涉及复杂场景的空间结构。然而，开发这一能力受到标注大量且组合性问题的成本限制。我们提出GeoX，一种通过可执行程序产生可验证奖励的自我对战框架，无需依赖大规模人工标注数据。给定卫星或航空图像，我们的框架采用单一多模态策略，提出空间问题作为可执行程序，并在三种推理模式（演绎、归纳和演绎）下通过空间原语和图像理解工具解决这些问题。验证器执行每个程序以产生奖励信号，通过强化学习联合优化两个角色。GeoX在平均上将基础VLMs提升高达5.5个百分点，与在数百万标注数据上训练的常规基线相匹配或超过。同时，我们发布了通过自我对战积累的地理空间理解基准测试。
英文摘要：
Geospatial reasoning requires solving image-grounded problems over the complex spatial structure of a scene. However, developing this capability is hindered by the cost of annotating a vast and combinatorial question space. We propose GeoX, a self-play framework that acquires spatial logic through executable programs that yield verifiable rewards, without relying on large-scale human-curated data Given a satellite or aerial image, our framework employs a single multimodal policy that proposes spatial problems as executable programs and solves them under three reasoning modes-abduction, deduction, and induction-over spatial primitives and an image understanding tool. A verifier executes each program to covert a reward signal that jointly optimizes the two roles via reinforcement learning. GeoX consistently improves its base VLMs by up to 5.5 points on average, matching or exceeding conventional baselines trained on millions of curated data. Along-side the proposed method, we release a benchmark for geospatial understanding accumulated through self-play.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
