kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Siva, Rohan, Cheung, Kai, Li, Lichi, Sundaram, Ganesh
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918400349962240
author Siva, Rohan
Cheung, Kai
Li, Lichi
Sundaram, Ganesh
author_facet Siva, Rohan
Cheung, Kai
Li, Lichi
Sundaram, Ganesh
contents Modern machine learning systems rely on complex data engineering workflows to extract, transform, and load (ELT) data into production pipelines. However, constructing these pipelines remains time-consuming and requires substantial expertise in data infrastructure and orchestration frameworks. Recent advances in large language model (LLM) agents offer a potential path toward automating these workflows, but existing approaches struggle with under-specified user intent, unreliable tool generation, and limited guarantees of executable outputs. We introduce kRAIG, an AI agent that translates natural language specifications into production-ready Kubeflow Pipelines (KFP). To resolve ambiguity in user intent, we propose ReQuesAct (Reason, Question, Act), an interaction framework that explicitly clarifies intent prior to pipeline synthesis. The system orchestrates end-to-end data movement from diverse sources and generates task-specific transformation components through a retrieval-augmented tool synthesis process. To ensure data quality and safety, kRAIG incorporates LLM-based validation stages that verify pipeline integrity prior to execution. Our framework achieves a 3x improvement in extraction and loading success and a 25 percent increase in transformation accuracy compared to state-of-the-art agentic baselines. These improvements demonstrate that structured agent workflows with explicit intent clarification and validation significantly enhance the reliability and executability of automated data engineering pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20311
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation
Siva, Rohan
Cheung, Kai
Li, Lichi
Sundaram, Ganesh
Software Engineering
Artificial Intelligence
Computation and Language
Modern machine learning systems rely on complex data engineering workflows to extract, transform, and load (ELT) data into production pipelines. However, constructing these pipelines remains time-consuming and requires substantial expertise in data infrastructure and orchestration frameworks. Recent advances in large language model (LLM) agents offer a potential path toward automating these workflows, but existing approaches struggle with under-specified user intent, unreliable tool generation, and limited guarantees of executable outputs. We introduce kRAIG, an AI agent that translates natural language specifications into production-ready Kubeflow Pipelines (KFP). To resolve ambiguity in user intent, we propose ReQuesAct (Reason, Question, Act), an interaction framework that explicitly clarifies intent prior to pipeline synthesis. The system orchestrates end-to-end data movement from diverse sources and generates task-specific transformation components through a retrieval-augmented tool synthesis process. To ensure data quality and safety, kRAIG incorporates LLM-based validation stages that verify pipeline integrity prior to execution. Our framework achieves a 3x improvement in extraction and loading success and a 25 percent increase in transformation accuracy compared to state-of-the-art agentic baselines. These improvements demonstrate that structured agent workflows with explicit intent clarification and validation significantly enhance the reliability and executability of automated data engineering pipelines.
title kRAIG: A Natural Language-Driven Agent for Automated DataOps Pipeline Generation
topic Software Engineering
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2603.20311