GeoSolver: Scaling Test-Time Reasoning in Remote Sensing with Fine-Grained Process Supervision
GeoSolver: 利用细粒度过程监督扩展遥感中的测试时推理
机构 * College of Computer Science and Technology(计算机科学与技术学院) ; Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University(教育部符号计算与知识工程重点实验室)
专题命中 推理与问题求解 :language model(abstract)
AI总结 提出GeoSolver框架,通过构建大规模过程监督数据集Geo-PRM-2M和训练过程奖励模型GeoPRM,结合过程感知树GRPO强化学习算法,实现遥感中可验证的逐步推理,在多个基准上达到最优性能并支持测试时扩展。
Comments Code: https://github.com/yourname/GeoSolver