# MontePrep: Monte-Carlo-Driven Automatic Data Preparation without Target Data Instances

arXiv: https://arxiv.org/abs/2509.17553 · HTML: https://mlsanity.com/paper/2509.17553/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 43 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Builds on (most cited first, 6 of 6)

- [Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding](https://mlsanity.com/paper/2401.04398/) (2024)
- [Auto-Tables: Synthesizing Multi-Step Transformations to Relationalize Tables without Using Examples](https://mlsanity.com/paper/2307.14565/) (2023)
- [Auto-Pipeline: Synthesizing Complex Data Pipelines By-Target Using Reinforcement Learning and Search](https://mlsanity.com/paper/2106.13861/) (2021)
- [Automatic Data Transformation Using Large Language Model: An Experimental Study on Building Energy Data](https://mlsanity.com/paper/2309.01957/) (2023)
- [Auto-Prep: Holistic Prediction of Data Preparation Steps for Self-Service Business Intelligence](https://mlsanity.com/paper/2504.11627/) (2025)
- [Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines](https://mlsanity.com/paper/2505.15874/) (2025)

## Built on by (most cited first, 1 of 1)

- [BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence](https://mlsanity.com/paper/2609.20886/) (2026)

## Abstract (arXiv)

In commercial systems, a pervasive requirement for automatic data preparation (ADP) is to transfer relational data from disparate sources to targets with standardized schema specifications. Previous methods rely on labor-intensive supervision signals or target table data access permissions, limiting their usage in real-world scenarios. To tackle these challenges, we propose an effective end-to-end ADP framework MontePrep, which enables training-free pipeline synthesis with zero target-instance requirements. MontePrep is formulated as an open-source large language model (LLM) powered tree-structured search problem. It consists of three pivot components, i.e., a data preparation action sandbox (DPAS), a fundamental pipeline generator (FPG), and an execution-aware pipeline optimizer (EPO). We first introduce DPAS, a lightweight action sandbox, to navigate the search-based pipeline generation. The design of DPAS circumvents exploration of infeasible pipelines. Then, we present FPG to build executable DP pipelines incrementally, which explores the predefined action sandbox by the LLM-powered Monte Carlo Tree Search. Furthermore, we propose EPO, which invokes pipeline execution results from sources to targets to evaluate the reliability of the generated pipelines in FPG. In this way, unreasonable pipelines are eliminated, thus facilitating the search process from both efficiency and effectiveness perspectives. Extensive experimental results demonstrate the superiority of MontePrep with significant improvement against five state-of-the-art competitors.