Table Question Answering (TQA) aims to answer natural language questions over structured tables. Large Language Models (LLMs) enable promising solutions to this problem, with operator-centric solutions that generate table manipulation pipelines in a multi-step manner offering state-of-the-art performance. However, these solutions rely on multiple LLM calls, resulting in prohibitive latencies and computational costs. We propose Operation-R1, the first framework that trains lightweight LLMs (e.g., Qwen-4B/1.7B) via a novel variant of reinforcement learning with verifiable rewards to produce high-quality data-preparation pipelines for TQA in a single inference step. To train such an LLM, we first introduce a self-supervised rewarding mechanism to automatically obtain fine-grained pipeline-wise supervision signals for LLM training. We also propose variance-aware group resampling to mitigate training instability. To further enhance robustness of pipeline generation, we develop two complementary mechanisms: operation merge, which filters spurious operations through multi-candidate consensus, and adaptive rollback, which offers runtime protection against information loss in data transformation. Experiments on two benchmark datasets show that, with the same LLM backbone, Operation-R1 achieves average absolute accuracy gains of 8.83 and 4.44 percentage points over multi-step preparation baselines, with 79\% table compression and a 2.2$\times$ reduction in monetary cost.

翻译：表格问答旨在解答针对结构化表格的自然语言问题。大型语言模型通过以操作符为核心、多步生成表格操作流水线的解决方案，为该问题提供了极具前景的方法，并取得了最先进的性能。然而，这些方案依赖多次调用大型语言模型，导致延迟难以承受且计算成本高昂。我们提出了Operation-R1，这是首个通过一种基于可验证奖励的新型强化学习方法训练轻量级大语言模型（如Qwen-4B/1.7B），使其能够在单次推理步骤中生成高质量数据准备流水线的框架。为了训练此类大语言模型，我们首先引入了一种自监督奖励机制，以自动获取细粒度的、基于流水线的监督信号用于模型训练。同时，我们提出方差感知组重采样技术以缓解训练不稳定性。为进一步增强流水线生成的鲁棒性，我们开发了两种互补机制：操作融合——通过多候选一致性过滤虚假操作；以及自适应回滚——为数据转换过程中的信息丢失提供运行时保护。在两个基准数据集上的实验表明，在相同的大语言模型骨干下，与多步准备基线相比，Operation-R1在平均绝对准确率上取得了8.83和4.44个百分点的提升，同时实现了79%的表格压缩和2.2倍的货币成本降低。