# AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework

arXiv: https://arxiv.org/abs/2412.10422 · HTML: https://mlsanity.com/paper/2412.10422/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 30 of its 64 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 30 of 30)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate](https://mlsanity.com/paper/2308.07201/) (2023)
- [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)
- [Long-context LLMs Struggle with Long In-context Learning](https://mlsanity.com/paper/2404.02060/) (2024)
- [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)
- [FEVEROUS: Fact Extraction and VERification Over Unstructured and Structured information](https://mlsanity.com/paper/2106.05707/) (2021)
- [MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution](https://mlsanity.com/paper/2403.17927/) (2024)
- [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)
- [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024)
- [Self-Organized Agents: A LLM Multi-Agent Framework toward Ultra Large-Scale Code Generation and Optimization](https://mlsanity.com/paper/2404.02183/) (2024)
- [ReAcTable: Enhancing ReAct for Table Question Answering](https://mlsanity.com/paper/2310.00815/) (2023)
- [Large Language Model for Table Processing: A Survey](https://mlsanity.com/paper/2402.05121/) (2024)
- [A Survey on Table Question Answering: Recent Advances](https://mlsanity.com/paper/2207.05270/) (2022)
- [PASTA: Table-Operations Aware Fact Verification via Sentence-Table Cloze Pre-training](https://mlsanity.com/paper/2211.02816/) (2022)
- [Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning](https://mlsanity.com/paper/1901.08492/) (2019)
- [MultiTabQA: Generating Tabular Answers for Multi-Table Question Answering](https://mlsanity.com/paper/2305.12820/) (2023)
- [DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filtering](https://mlsanity.com/paper/1911.00061/) (2019)
- [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)
- [DataPrep.EDA: Task-Centric Exploratory Data Analysis for Statistical Modeling in Python](https://mlsanity.com/paper/2104.00841/) (2021)

## Built on by (most cited first, 12 of 12)

- [KramaBench: A Benchmark for AI Systems on Data-to-Insight Pipelines over Data Lakes](https://mlsanity.com/paper/2506.06541/) (2025)
- [A Survey of Data Agents: Emerging Paradigm or Overstated Hype?](https://mlsanity.com/paper/2510.23587/) (2025)
- [Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards](https://mlsanity.com/paper/2505.04671/) (2025)
- [Text-to-Pipeline: Bridging Natural Language and Data Preparation Pipelines](https://mlsanity.com/paper/2505.15874/) (2025)
- [Automatic End-to-End Data Integration using Large Language Models](https://mlsanity.com/paper/2603.10547/) (2026)
- [PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?](https://mlsanity.com/paper/2605.08687/) (2026)
- [stratum: A System Infrastructure for Massive Agent-Centric ML Workloads](https://mlsanity.com/paper/2603.03589/) (2026)
- [BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting](https://mlsanity.com/paper/2605.17937/) (2026)
- [Accurate Table Question Answering with Accessible LLMs](https://mlsanity.com/paper/2601.03137/) (2026)
- [Replacing Multi-Step Assembly of Data Preparation Pipelines with One-Step LLM Pipeline Generation for Table QA](https://mlsanity.com/paper/2602.22721/) (2026)
- [DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering](https://mlsanity.com/paper/2603.09152/) (2026)
- [Graph, Loop, and Harness Engineering for Zero-Trust Agentic Data Engineering and Analytical Processing](https://mlsanity.com/paper/2609.29668/) (2026)

## Abstract (arXiv)

Answering natural language (NL) questions about tables, known as Tabular Question Answering (TQA), is crucial because it allows users to quickly and efficiently extract meaningful insights from structured data, effectively bridging the gap between human language and machine-readable formats. Many of these tables are derived from web sources or real-world scenarios, which require meticulous data preparation (or data prep) to ensure accurate responses. However, preparing such tables for NL questions introduces new requirements that extend beyond traditional data preparation. This question-ware data preparation involves specific tasks such as column derivation and filtering tailored to particular questions, as well as question-aware value normalization or conversion, highlighting the need for a more nuanced approach in this context. Because each of the above tasks is unique, a single model (or agent) may not perform effectively across all scenarios. In this paper, we propose AutoPrep, a large language model (LLM)-based multiagent framework that leverages the strengths of multiple agents, each specialized in a certain type of data prep, ensuring more accurate and contextually relevant responses. Given an NL question over a table, AutoPrep performs data prep through three key components. Planner: Determines a logical plan, outlining a sequence of high-level operations. Programmer: Translates this logical plan into a physical plan by generating the corresponding low-level code. Executor: Executes the generated code to process the table. To support this multi-agent framework, we design a novel Chain-ofClauses reasoning mechanism for high-level operation suggestion, and a tool-augmented method for low-level code generation.