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

• URL: http://arxiv.org/abs/2510.24339v2
• Date: Wed, 29 Oct 2025 04:05:13 GMT
• Title: VDSAgents: A PCS-Guided Multi-Agent System for Veridical Data Science Automation
• Authors: Yunxuan Jiang, Silan Hu, Xiaoning Wang, Yuanyuan Zhang, Xiangyu Chang,
• Abstract summary: Large language models (LLMs) become increasingly integrated into data science for automated system design.<n>This paper provides VDSAgents, a multi-agent system grounded in the Predictability-Computability-Stability (PCS) principles.<n>We evaluate VDSAgents on nine datasets with diverse characteristics, comparing it with state-of-the-art end-to-end data science systems.
• Score: 11.521235834823301
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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, a multi-agent system grounded in the Predictability-Computability-Stability (PCS) principles proposed in the Veridical Data Science (VDS) framework. 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.

Related papers

• An Agentic Framework for Autonomous Materials Computation [70.24472585135929]
  Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery.<n>Recent advances integrate LLMs into agentic frameworks, enabling retrieval, reasoning, and tool use for complex scientific experiments.<n>Here, we present a domain-specialized agent designed for reliable automation of first-principles materials computations.
  arXiv  Detail & Related papers  (2025-12-22T15:03:57Z)
• Multi-Agent Systems for Dataset Adaptation in Software Engineering: Capabilities, Limitations, and Future Directions [8.97512410819274]
  This paper presents the first empirical study on how state-of-the-art multi-agent systems perform in dataset adaptation tasks.<n>We evaluate GitHub Copilot on adapting SE research artifacts from benchmark repositories including ROCODE and LogHub2.0.<n>Results show that current systems can identify key files and generate partial adaptations but rarely produce correct implementations.
  arXiv  Detail & Related papers  (2025-11-26T13:26:11Z)
• Dataforge: A Data Agent Platform for Autonomous Data Engineering [22.691284342164334]
  Data Agent is a fully autonomous system specialized for tabular data.<n>It automatically performs data cleaning, hierarchical routing, and feature-level optimization through dual feedback loops.<n>It embodies three core principles: automatic, safe, and non-expert friendly, which ensure end-to-end reliability without human supervision.
  arXiv  Detail & Related papers  (2025-11-09T01:58:13Z)
• A Survey of Data Agents: Emerging Paradigm or Overstated Hype? [66.1526688475023]
  "Data agent" currently suffers from terminological ambiguity and inconsistent adoption.<n>This survey introduces the first systematic hierarchical taxonomy for data agents.<n>We conclude with a forward-looking roadmap, envisioning the advent of proactive, generative data agents.
  arXiv  Detail & Related papers  (2025-10-27T17:54:07Z)
• Autonomous Data Agents: A New Opportunity for Smart Data [50.02229219403014]
  Report argues that DataAgents represent a paradigm shift toward autonomous data-to-knowledge systems.<n>DataAgents transform complex and unstructured data into coherent and actionable knowledge.<n>We first examine why the convergence of agentic AI and data-to-knowledge systems has emerged as a critical trend.
  arXiv  Detail & Related papers  (2025-09-23T06:46:41Z)
• Data Shift of Object Detection in Autonomous Driving [0.40792653193642503]
  We study the data shift problem in autonomous driving object detection tasks.<n>We employ shift detection analysis techniques to perform dataset categorization and balancing.<n>To validate our approach, we optimize the model by integrating CycleGAN-based data augmentation techniques with the YOLOv5 framework.
  arXiv  Detail & Related papers  (2025-08-16T01:52:31Z)
• GateLens: A Reasoning-Enhanced LLM Agent for Automotive Software Release Analytics [9.549568621873386]
  GateLens is an LLM-based system for analyzing data in the automotive domain.<n>Unlike traditional multi-agent or planning-based systems that can be slow, opaque, and costly to maintain, GateLens emphasizes speed, transparency, and reliability.
  arXiv  Detail & Related papers  (2025-03-27T17:48:32Z)
• DatawiseAgent: A Notebook-Centric LLM Agent Framework for Adaptive and Robust Data Science Automation [10.390461679868197]
  We introduce DatawiseAgent, a notebook-centric large language model (LLM) agent framework for adaptive and robust data science automation.<n>Inspired by how human data scientists work in computational notebooks, DatawiseAgent introduces a unified interaction representation and a multi-stage architecture.
  arXiv  Detail & Related papers  (2025-03-10T08:32:33Z)
• Meta-Statistical Learning: Supervised Learning of Statistical Inference [59.463430294611626]
  This work demonstrates that the tools and principles driving the success of large language models (LLMs) can be repurposed to tackle distribution-level tasks.<n>We propose meta-statistical learning, a framework inspired by multi-instance learning that reformulates statistical inference tasks as supervised learning problems.
  arXiv  Detail & Related papers  (2025-02-17T18:04:39Z)
• DSBench: How Far Are Data Science Agents from Becoming Data Science Experts? [58.330879414174476]
  We introduce DSBench, a benchmark designed to evaluate data science agents with realistic tasks.<n>This benchmark includes 466 data analysis tasks and 74 data modeling tasks, sourced from Eloquence and Kaggle competitions.<n>Our evaluation of state-of-the-art LLMs, LVLMs, and agents shows that they struggle with most tasks, with the best agent solving only 34.12% of data analysis tasks and achieving a 34.74% Relative Performance Gap (RPG)
  arXiv  Detail & Related papers  (2024-09-12T02:08:00Z)
• MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization [86.61052121715689]
  MatPlotAgent is a model-agnostic framework designed to automate scientific data visualization tasks. MatPlotBench is a high-quality benchmark consisting of 100 human-verified test cases.
  arXiv  Detail & Related papers  (2024-02-18T04:28:28Z)
• From Data to Actions in Intelligent Transportation Systems: a Prescription of Functional Requirements for Model Actionability [10.27718355111707]
  This work aims to describe how data, coming from diverse ITS sources, can be used to learn and adapt data-driven models for efficiently operating ITS assets, systems and processes. Grounded in this described data modeling pipeline for ITS, wedefine the characteristics, engineering requisites and intrinsic challenges to its three compounding stages, namely, data fusion, adaptive learning and model evaluation.
  arXiv  Detail & Related papers  (2020-02-06T12:02:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.