Dataforge: Agentic Platform for Autonomous Data Engineering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Xinyuan, Cao, Hongyu, Liu, Kunpeng, Fu, Yanjie
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908835111763968
author Wang, Xinyuan
Cao, Hongyu
Liu, Kunpeng
Fu, Yanjie
author_facet Wang, Xinyuan
Cao, Hongyu
Liu, Kunpeng
Fu, Yanjie
contents The growing demand for artificial intelligence (AI) applications in materials discovery, molecular modeling, and climate science has made data preparation a critical but labor-intensive bottleneck. Raw data from diverse sources must be cleaned, normalized, and transformed to become AI-ready, where effective feature transformation and selection are essential for robust learning. We present Dataforge, an LLM-powered agentic data engineering platform for tabular data that is automatic, safe, and non-expert friendly. It autonomously performs data cleaning and iteratively optimizes feature operations under a budgeted feedback loop with automatic stopping. Across tabular benchmarks, it achieves the best overall downstream performance; ablations further confirm the roles of routing/iterative refinement and grounding in accuracy and reliability. Dataforge demonstrates a practical path toward autonomous data agents that transform raw data from data to better data.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06185
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Dataforge: Agentic Platform for Autonomous Data Engineering
Wang, Xinyuan
Cao, Hongyu
Liu, Kunpeng
Fu, Yanjie
Artificial Intelligence
The growing demand for artificial intelligence (AI) applications in materials discovery, molecular modeling, and climate science has made data preparation a critical but labor-intensive bottleneck. Raw data from diverse sources must be cleaned, normalized, and transformed to become AI-ready, where effective feature transformation and selection are essential for robust learning. We present Dataforge, an LLM-powered agentic data engineering platform for tabular data that is automatic, safe, and non-expert friendly. It autonomously performs data cleaning and iteratively optimizes feature operations under a budgeted feedback loop with automatic stopping. Across tabular benchmarks, it achieves the best overall downstream performance; ablations further confirm the roles of routing/iterative refinement and grounding in accuracy and reliability. Dataforge demonstrates a practical path toward autonomous data agents that transform raw data from data to better data.
title Dataforge: Agentic Platform for Autonomous Data Engineering
topic Artificial Intelligence
url https://arxiv.org/abs/2511.06185