一句话：TestFlow 结合监督微调与任务感知强化学习，提升移动 UI 复杂多步测试的完成率与可靠性。
移动 UI 测试中，GUI Agent 已展现潜力，但面对复杂测试任务时，逐步贪心执行容易导致误差累积，并忽略长时程依赖，从而失败。本文提出 TestFlow，一种多模态 UI 测试模型，将监督微调与任务感知强化学习相结合，并设计两阶段训练流程，以优化长时程指令遵循和复杂任务完成能力。作者还提出定制奖励函数，融合过程奖励与结果奖励，提升多步任务完成率。在跨页面测试场景中，TestFlow 显著优于基线方法，达到 33.69% 的 WTSR 和 55.37% 的 SSR，表明其在现代移动应用测试，尤其是高适应性与高可靠性要求的工业场景中具有实用价值。
GUI Agents have demonstrated promising applications in mobile UI testing. However, for complex testing tasks, UI agents tend to fail due to their greedy approach in executing step-by-step operations, leading to error accumulation and neglecting long-horizon dependencies. To address these limitations, we propose TestFlow, a novel multi-modal UI testing model that combines Supervised Fine-Tuning with a Task-aware Reinforcement Learning framework. Our approach implements a two-phase training pipeline designed to optimize long-horizon instruction compliance and complex task completion. Additionally, we develop a tailor-made reward function that integrates both process and outcome rewards to improve the completion rate of multi-step tasks. The experimental results demonstrate that TestFlow significantly outperforms the baseline methods, achieving 33. 69% WTSR and 55. 37% SSR in cross-page test scenarios. These improvements highlight the practical value of TestFlow in addressing the challenges of modern mobile app testing, particularly in industrial settings requiring high adaptability and reliability.
@inproceedings{paperbot9585,
title = {TestFlow: Advancing Mobile UI Testing through Multi-Step Reinforcement Learning},
author = {Xiaoxuan Tang and Xinfang Chen and Dajun Chen and Sheng Zhou and Wei Jiang and Yong Li},
booktitle = {ISSTA},
year = {2025},
doi = {10.1145/3713081.3732930}
}