# Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QA

arXiv: https://arxiv.org/abs/2602.22721 · HTML: https://mlsanity.com/paper/2602.22721/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 40 references that are in the map.
- First posted on arXiv 26 Feb 2026.

## Builds on (most cited first, 26 of 26)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Tulu 3: Pushing Frontiers in Open Language Model Post-Training](https://mlsanity.com/paper/2411.15124/) (2024)
- [Compositional Semantic Parsing on Semi-Structured Tables](https://mlsanity.com/paper/1508.00305/) (2015)
- [TabFact: A Large-scale Dataset for Table-based Fact Verification](https://mlsanity.com/paper/1909.02164/) (2019)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024)
- [Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning](https://mlsanity.com/paper/2301.13808/) (2023)
- [FeTaQA: Free-form Table Question Answering](https://mlsanity.com/paper/2104.00369/) (2021)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [Large Language Models are few(1)-shot Table Reasoners](https://mlsanity.com/paper/2210.06710/) (2022)
- [ReAcTable: Enhancing ReAct for Table Question Answering](https://mlsanity.com/paper/2310.00815/) (2023)
- [SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers](https://mlsanity.com/paper/2407.09413/) (2024)
- [TableGPT2: A Large Multimodal Model with Tabular Data Integration](https://mlsanity.com/paper/2411.02059/) (2024)
- [Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay](https://mlsanity.com/paper/2506.05316/) (2025)
- [Tab-CoT: Zero-shot Tabular Chain of Thought](https://mlsanity.com/paper/2305.17812/) (2023)
- [Table-R1: Region-based Reinforcement Learning for Table Understanding](https://mlsanity.com/paper/2505.12415/) (2025)
- [Large Language Models are Complex Table Parsers](https://mlsanity.com/paper/2312.11521/) (2023)
- [Interpretable LLM-based Table Question Answering](https://mlsanity.com/paper/2412.12386/) (2024)
- [Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning](https://mlsanity.com/paper/2506.01710/) (2025)
- [TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering](https://mlsanity.com/paper/2506.03949/) (2025)
- [AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework](https://mlsanity.com/paper/2412.10422/) (2024)
- [MFORT-QA: Multi-hop Few-shot Open Rich Table Question Answering](https://mlsanity.com/paper/2403.19116/) (2024)
- [Unlocking the Potential of Difficulty Prior in RL-based Multimodal Reasoning](https://mlsanity.com/paper/2505.13261/) (2025)
- [Table-r1: Self-supervised and Reinforcement Learning for Program-based Table Reasoning in Small Language Models](https://mlsanity.com/paper/2506.06137/) (2025)
- [A-IPO: Adaptive Intent-driven Preference Optimization](https://mlsanity.com/paper/2510.10077/) (2025)

## Abstract (arXiv)

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× reduction in monetary cost.