Text-to-SQL has recently achieved impressive progress, yet remains difficult to apply effectively in real-world scenarios. This gap stems from the reliance on single static workflows, fundamentally limiting scalability to out-of-distribution and long-tail scenarios. Instead of requiring users to select suitable methods through extensive experimentation, we attempt to enable systems to adaptively construct workflows at inference time. Through theoretical and empirical analysis, we demonstrate that optimal dynamic policies consistently outperform the best static workflow, with performance gains fundamentally driven by heterogeneity across candidate workflows. Motivated by this, we propose SquRL, a reinforcement learning framework that enhances LLMs' reasoning capability in adaptive workflow construction. We design a rule-based reward function and introduce two effective training mechanisms: dynamic actor masking to encourage broader exploration, and pseudo rewards to improve training efficiency. Experiments on widely-used Text-to-SQL benchmarks demonstrate that dynamic workflow construction consistently outperforms the best static workflow methods, with especially pronounced gains on complex and out-of-distribution queries. The codes are available at https://github.com/Satissss/SquRL

翻译：文本到SQL技术近期取得了显著进展，但在实际应用场景中仍难以有效部署。这一差距源于对单一静态工作流的依赖，从根本上限制了模型在分布外场景和长尾场景中的可扩展性。不同于要求用户通过大量实验选择合适方法，我们尝试让系统能够在推理时自适应地构建工作流。通过理论与实证分析，我们证明最优动态策略始终优于最佳静态工作流，其性能提升从根本上源于候选工作流之间的异质性。受此启发，我们提出SquRL——一个增强大语言模型在自适应工作流构建中推理能力的强化学习框架。我们设计了基于规则的奖励函数，并引入两种有效的训练机制：动态参与者掩码以鼓励更广泛的探索，以及伪奖励以提高训练效率。在广泛使用的文本到SQL基准测试上的实验表明，动态工作流构建始终优于最佳静态工作流方法，在复杂查询和分布外查询上提升尤为显著。代码已发布于 https://github.com/Satissss/SquRL