Reinforcement Learning (RL) has become a promising approach for improving GUI Agents in long-horizon, stochastic digital environments, but trajectory-level success feedback is too sparse to provide reliable credit assignment for intermediate exploration steps. To mitigate this issue, recent studies introduce Process Reward Models (PRMs), which provide finer-grained training feedback through global milestone verification or local step-level evaluation. However, these methods still suffer from two level-specific limitations: global milestone decomposition is subjective and singular, making it difficult to accommodate the multiple valid execution paths in real GUI tasks, while fixed local judging windows may miss long-range key evidence or dilute the decision signal with irrelevant frames. Inspired by stain-tracing mechanisms in network flow analysis, we propose StainFlow, an entity-stain-flow process reward model for GUI Agents. To reduce the subjectivity of global partitioning, we introduce the Global Entity Stain Tracking module, which extracts visually verifiable task entities and tracks how their stain concentrations and states evolve along the trajectory, allowing task phases to be objectively separated by changes in the entity evidence flow. To improve the accuracy of local verification, we introduce the Local Stain Evidence Linking module. Centered on the triggering entities of each candidate key node, it retrieves relevant steps based on their stain concentrations and state changes, and dynamically constructs high-density evidence windows for verifying true key nodes. Extensive experiments on AndroidWorld and OGRBench show that StainFlow relatively improves online RL success by 3.2% and trajectory completion judgment accuracy by 1.8%.

翻译：强化学习（RL）已成为在长视距、随机数字环境中提升GUI代理性能的重要途径，但轨迹级成功反馈过于稀疏，难以对中间探索步骤提供可靠的信用分配。为解决该问题，近期研究引入过程奖励模型（PRM），通过全局里程碑验证或局部步骤级评估提供更细粒度的训练反馈。然而，这些方法仍存在两个层级特有的局限：全局里程碑分解具有主观性与单一性，难以适应真实GUI任务中多重有效执行路径；而固定的局部判断窗口可能遗漏长距离关键证据，或因无关帧稀释决策信号。受网络流分析中印记追踪机制启发，本文提出StainFlow——一种面向GUI代理的实体印记流过程奖励模型。为降低全局划分的主观性，引入全局实体印记追踪模块，提取可视觉验证的任务实体，并追踪其印记浓度与状态沿轨迹的演化过程，从而依据实体证据流的变化客观分离任务阶段。为提升局部验证的准确性，引入局部印记证据关联模块。该模块以每个候选关键节点的触发实体为中心，依据其印记浓度与状态变化检索相关步骤，动态构建高密度证据窗口以验证真实关键节点。在AndroidWorld与OGRBench上的广泛实验表明，StainFlow在在线RL成功率上相对提升3.2%，在轨迹完成判断准确率上相对提升1.8%。