Satellite-to-radar (S2R) retrieval estimates ground radar precipitation from geostationary satellite observations, providing a critical solution for precipitation monitoring in radar-sparse regions. However, S2R retrieval is intrinsically ill-posed: similar cloud-top radiances can correspond to distinct precipitation regimes, storm organizations, and surface intensities, which are difficult to uniquely determine the underlying meteorological state from local spectral cues alone. Meteorological semantics offer complementary scene-level information that can help resolve this ambiguity. Yet existing static semantic conditioning is often insufficient, as externally predefined semantics cannot adapt to dynamic convective scenes or align with retrieval objectives. To this end, we propose LangRetrieval, a language-guided conditional flow matching (CFM) framework that establishes a closed-loop optimization mechanism between meteorological semantics and retrieval accuracy. Specifically, LangRetrieval consists of two core components: (i) Semantic Warm-up: structured meteorological attributes are injected into the CFM backbone through cross-attention conditioning, enabling continuous semantic guidance throughout the generation trajectory; and (ii) Self-Evolving Semantic Optimization: a lightweight attribute policy is first initialized from vision-language model annotations and subsequently refined via Group Relative Policy Optimization (GRPO) using multi-threshold Critical Success Index (CSI) rewards, enabling semantic generation to evolve directly toward improved retrieval accuracy.

翻译：卫星至雷达反演（S2R retrieval）通过静止卫星观测估计地面雷达降水，为雷达稀疏区域的降水监测提供了关键解决方案。然而，S2R反演本质上具有不适定性：相似的云顶辐射率可能对应不同的降水机制、风暴组织和地表强度，难以仅凭局地光谱特征唯一确定潜在的气象状态。气象语义提供了可辅助消解该歧义性的场景级补充信息。然而，现有静态语义约束往往不足——外部预定义的语义无法适应动态对流场景，亦难以与反演目标对齐。为此，我们提出LangRetrieval——一种语言引导的条件流匹配框架，在气象语义与反演精度之间建立闭环优化机制。具体而言，LangRetrieval包含两大核心组件：(i) 语义预热：通过交叉注意力条件注入结构化气象属性至CFM骨干网络，在生成全轨迹中实现持续语义引导；(ii) 自演化语义优化：首先基于视觉-语言模型标注初始化轻量级属性策略，随后采用多阈值临界成功指数奖励，通过组相对策略优化对策略进行精炼，使语义生成直接朝向反演精度提升的方向演化。