# Dango: A Mixed-Initiative Data Wrangling System using Large Language Model

arXiv: https://arxiv.org/abs/2503.03154 · HTML: https://mlsanity.com/paper/2503.03154/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Mar 2025.

## Built on by (most cited first, 5 of 5)

- [PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?](https://mlsanity.com/paper/2605.08687/) (2026)
- [Knowing Isn't Understanding: Re-grounding Generative Proactivity with Epistemic and Behavioral Insight](https://mlsanity.com/paper/2602.15259/) (2026)
- [How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning](https://mlsanity.com/paper/2605.23023/) (2026)
- [Plans Work in Mysterious Ways: Evaluating a Plan Mode for Spreadsheet Agents](https://mlsanity.com/paper/2607.23670/) (2026)
- [Exploring Agentic Approaches for Data Issue Detection and Repair in AI-Assisted Visualization](https://mlsanity.com/paper/2608.21602/) (2026)

## Abstract (arXiv)

Data wrangling is a time-consuming and challenging task in a data science pipeline. While many tools have been proposed to automate or facilitate data wrangling, they often misinterpret user intent, especially in complex tasks. We propose Dango, a mixed-initiative multi-agent system for data wrangling. Compared to existing tools, Dango enhances user communication of intent by allowing users to demonstrate on multiple tables and use natural language prompts in a conversation interface, enabling users to clarify their intent by answering LLM-posed multiple-choice clarification questions, and providing multiple forms of feedback such as step-by-step natural language explanations and data provenance to help users evaluate the data wrangling scripts. We conducted a within-subjects user study with 38 participants and demonstrated that Dango's features can significantly improve intent clarification, accuracy, and efficiency in data wrangling. Furthermore, we demonstrated the generalizability of Dango by applying it to a broader set of data wrangling tasks.