# MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems

arXiv: https://arxiv.org/abs/2608.16181 · HTML: https://mlsanity.com/paper/2608.16181/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 62 references that are in the map.
- First posted on arXiv 17 Aug 2026.

## 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, 12 of 12)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [Grounded Copilot: How Programmers Interact with Code-Generating Models](https://mlsanity.com/paper/2206.15000/) (2022)
- [DeepAnalyze: Agentic Large Language Models for Autonomous Data Science](https://mlsanity.com/paper/2510.16872/) (2025)
- [AutoDS: Towards Human-Centered Automation of Data Science](https://mlsanity.com/paper/2101.05273/) (2021)
- [Data Formulator: AI-powered Concept-driven Visualization Authoring](https://mlsanity.com/paper/2309.10094/) (2023)
- [Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition](https://mlsanity.com/paper/2407.02651/) (2024)
- [Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows](https://mlsanity.com/paper/2507.08149/) (2025)
- [Data Formulator 2: Iterative Creation of Data Visualizations, with AI Transforming Data Along the Way](https://mlsanity.com/paper/2408.16119/) (2024)
- [Just-In-Time Objectives: A General Approach for Specialized AI Interactions](https://mlsanity.com/paper/2510.14591/) (2025)
- [DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent Behaviors](https://mlsanity.com/paper/2602.05446/) (2026)

## Abstract (arXiv)

Recent advances in large language models have enabled a new class of agentic data science systems that allow users to complete complex data science workflows through natural language. Although these systems can significantly reduce manual effort, it remains difficult to diagnose their behavior and steer the reasoning process when failures or unexpected outputs occur. We present MUSE, an interactive meta-agent that enhances user understanding and control of agentic data science systems by (1) dynamically restructuring low-level execution traces into multiple semantic levels that support navigation from high-level overviews to low-level implementation details; (2) enabling users to reference specific workflow steps in context to ask grounded questions, provide feedback, and revise problematic steps without manually locating relevant execution history; and (3) supporting mixed-initiative steering by surfacing suspicious steps for inspection, scaffolding the repair process, and translating user repair intent into contextualized instructions for the underlying agent. In a between-subjects study (n = 15), MUSE improved task efficiency and increased users' confidence in understanding and steering agentic data science workflows.