# Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search

arXiv: https://arxiv.org/abs/2106.13861 · HTML: https://mlsanity.com/paper/2106.13861/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 71 references that are in the map.
- First posted on arXiv 25 Jun 2021.

## Builds on (most cited first, 7 of 7)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [Deep Entity Matching with Pre-Trained Language Models](https://mlsanity.com/paper/2004.00584/) (2020)
- [HoloClean: Holistic Data Repairs with Probabilistic Inference](https://mlsanity.com/paper/1702.00820/) (2017)
- [HoloDetect: Few-Shot Learning for Error Detection](https://mlsanity.com/paper/1904.02285/) (2019)
- [End-to-End Entity Resolution for Big Data: A Survey](https://mlsanity.com/paper/1905.06397/) (2019)
- [Searching a Database of Source Codes Using Contextualized Code Search](https://mlsanity.com/paper/2001.03277/) (2020)

## Built on by (most cited first, 8 of 8)

- [Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples](https://mlsanity.com/paper/2307.14565/) (2023)
- [AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework](https://mlsanity.com/paper/2412.10422/) (2024)
- [Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data](https://mlsanity.com/paper/2310.02540/) (2023)
- [AutoML in Heavily Constrained Applications](https://mlsanity.com/paper/2306.16913/) (2023)
- [Automatic End-to-End Data Integration using Large Language Models](https://mlsanity.com/paper/2603.10547/) (2026)
- [KGLiDS: A Platform for Semantic Abstraction, Linking, and Automation of Data Science](https://mlsanity.com/paper/2303.02204/) (2023)
- [MontePrep: Monte-Carlo-Driven Automatic Data Preparation without Target Data Instances](https://mlsanity.com/paper/2509.17553/) (2025)
- [FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction](https://mlsanity.com/paper/2606.24679/) (2026)

## Abstract (arXiv)

Recent work has made significant progress in helping users to automate single data preparation steps, such as string-transformations and table-manipulation operators (e.g., Join, GroupBy, Pivot, etc.). We in this work propose to automate multiple such steps end-to-end, by synthesizing complex data pipelines with both string transformations and table-manipulation operators. We propose a novel "by-target" paradigm that allows users to easily specify the desired pipeline, which is a significant departure from the traditional by-example paradigm. Using by-target, users would provide input tables (e.g., csv or json files), and point us to a "target table" (e.g., an existing database table or BI dashboard) to demonstrate how the output from the desired pipeline would schematically "look like". While the problem is seemingly underspecified, our unique insight is that implicit table constraints such as FDs and keys can be exploited to significantly constrain the space to make the problem tractable. We develop an Auto-Pipeline system that learns to synthesize pipelines using reinforcement learning and search. Experiments on large numbers of real pipelines crawled from GitHub suggest that Auto-Pipeline can successfully synthesize 60-70% of these complex pipelines with up to 10 steps.