EUVIMEDEUVIMED entdecken
Crossref

VDSAgents: A PCS‐Guided Multi‐Agent System for Veridical Data Science Automation

Yunxuan Jiang, Silan Hu, Xiaoning Wang, Yuanyuan Zhang, Xiangyu Chang

Stat · 2026-03 · 15 (1)

DOI: 10.1002/sta4.70126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Stat, online erschienen am 05.01.2026. Verfasst von Yunxuan Jiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 25 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) become increasingly integrated into data science workflows for automated system design. However, these LLM‐driven data science systems rely solely on the internal reasoning of LLMs, lacking guidance from scientific and theoretical principles. This limits their trustworthiness and robustness, especially when dealing with noisy and complex real‐world datasets. This paper provides VDSAgents 1 , a multi‐agent system grounded in the predictability–computability–stability (PCS) principles (Yu and Kumbier, 2020). proposed in the veridical data science (VDS) (Yu and Barter, 2024). Guided by PCS principles, the system implements a modular workflow for data cleaning, feature engineering, modeling and evaluation. Each phase is handled by an elegant agent, incorporating perturbation analysis, unit testing and model validation to ensure both functionality and scientific auditability. We evaluate VDSAgents on nine datasets with diverse characteristics, comparing it with state‐of‐the‐art end‐to‐end data science systems, such as AutoKaggle and DataInterpreter , using DeepSeek‐V3 and GPT‐4o as backends. VDSAgents consistently outperforms the results of AutoKaggle and DataInterpreter , which validates the feasibility of embedding PCS principles into LLM‐driven data science automation.

Zitieren

APA

Jiang, Y., Hu, S., Wang, X., Zhang, Y., & Chang, X. (2026). VDSAgents: A PCS‐Guided Multi‐Agent System for Veridical Data Science Automation. Stat, 15(1). https://doi.org/10.1002/sta4.70126

Vancouver

Jiang Y, Hu S, Wang X, Zhang Y, Chang X. VDSAgents: A PCS‐Guided Multi‐Agent System for Veridical Data Science Automation. Stat. 2026;15(1). doi:10.1002/sta4.70126

BibTeX
@article{Jiang2026,
  author = {Jiang, Yunxuan and Hu, Silan and Wang, Xiaoning and Zhang, Yuanyuan and Chang, Xiangyu},
  title = {VDSAgents: A PCS‐Guided Multi‐Agent System for Veridical Data Science Automation},
  journal = {Stat},
  year = {2026},
  volume = {15},
  number = {1},
  doi = {10.1002/sta4.70126}
}
Kostenlos starten →