Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?

TL;DR

Spider2-V introduces a comprehensive benchmark to evaluate multimodal agents' ability to automate complex data science workflows, revealing current limitations and guiding future improvements in AI automation tools.

Contribution

This paper presents the first multimodal agent benchmark for enterprise data workflows, including real-world tasks, evaluation metrics, and insights into current agent performance.

Findings

Existing agents achieve only 14% success in full workflows.

Agents struggle with fine-grained GUI actions, with only 16.2% success.

Performance drops further to 10.6% in cloud-based environments.

Abstract

Data science and engineering workflows often span multiple stages, from warehousing to orchestration, using tools like BigQuery, dbt, and Airbyte. As vision language models (VLMs) advance in multimodal understanding and code generation, VLM-based agents could potentially automate these workflows by generating SQL queries, Python code, and GUI operations. This automation can improve the productivity of experts while democratizing access to large-scale data analysis. In this paper, we introduce Spider2-V, the first multimodal agent benchmark focusing on professional data science and engineering workflows, featuring 494 real-world tasks in authentic computer environments and incorporating 20 enterprise-level professional applications. These tasks, derived from real-world use cases, evaluate the ability of a multimodal agent to perform data-related tasks by writing code and managing the GUI in enterprise data software systems. To balance realistic simulation with evaluation simplicity, we devote significant effort to developing automatic configurations for task setup and carefully crafting evaluation metrics for each task. Furthermore, we supplement multimodal agents with comprehensive documents of these enterprise data software systems. Our empirical evaluation reveals that existing state-of-the-art LLM/VLM-based agents do not reliably automate full data workflows (14.0% success). Even with step-by-step guidance, these agents still underperform in tasks that require fine-grained, knowledge-intensive GUI actions (16.2%) and involve remote cloud-hosted workspaces (10.6%). We hope that Spider2-V paves the way for autonomous multimodal agents to transform the automation of data science and engineering workflow. Our code and data are available at https://spider2-v.github.io.