MUSE: An Interactive Meta-Agent for Understanding and Steering LLM-powered Data Science Systems
2026-08-17 • Human-Computer Interaction
Human-Computer InteractionArtificial Intelligence
AI summaryⓘ
The authors created MUSE, a tool that helps people understand and control AI systems used for data science tasks done through natural language. MUSE organizes the detailed steps these AI systems take into simpler, meaningful layers so users can see both the big picture and small details. It also lets users ask questions or fix parts of the workflow without digging through complex histories. In tests, MUSE helped users work faster and feel more confident managing these AI-powered data science tasks.
large language modelsagentic systemsdata science workflowsexecution tracesuser interactionmixed-initiative steeringworkflow debugginghuman-AI collaboration
Authors
Wei-Hao Chen, Weixi Tong, Yuan Tian, Chenglong Wang, Tianyi Zhang
Abstract
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.