Saved in:
Bibliographic Details
Main Authors: Bara, Adela, Dobrita, Gabriela, Oprea, Simona-Vasilica
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.27096
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910177885683712
author Bara, Adela
Dobrita, Gabriela
Oprea, Simona-Vasilica
author_facet Bara, Adela
Dobrita, Gabriela
Oprea, Simona-Vasilica
contents The purpose of our paper is to develop a unified multi-agent architecture that automates end-to-end machine learning (ML) pipeline generation from datasets and natural-language (NL) goals, improving efficiency, robustness and explainability. A five-agent system is proposed to handle profiling, intent parsing, microservice recommendation, Directed Acyclic Graph (DAG) construction and execution. It integrates code-grounded Retrieval-Augmented Generation (RAG) for microservice understanding, an explainable hybrid recommender combining multiple criteria, a self-healing mechanism using Large Language Model (LLM)-based error interpretation and adaptive learning from execution history. The approach is evaluated on 150 ML tasks across diverse scenarios. The system achieves an 84.7% end-to-end pipeline success rate, outperforming baseline methods. It demonstrates improved robustness through self-healing and reduces workflow development time compared to manual construction. The study introduces a novel integration of code-grounded RAG, explainable recommendation, self-healing execution and adaptive learning within a single architecture, showing that tightly coupled intelligent components can outperform isolated solutions.
format Preprint
id arxiv_https___arxiv_org_abs_2604_27096
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Think it, Run it: Autonomous ML pipeline generation via self-healing multi-agent AI
Bara, Adela
Dobrita, Gabriela
Oprea, Simona-Vasilica
Artificial Intelligence
The purpose of our paper is to develop a unified multi-agent architecture that automates end-to-end machine learning (ML) pipeline generation from datasets and natural-language (NL) goals, improving efficiency, robustness and explainability. A five-agent system is proposed to handle profiling, intent parsing, microservice recommendation, Directed Acyclic Graph (DAG) construction and execution. It integrates code-grounded Retrieval-Augmented Generation (RAG) for microservice understanding, an explainable hybrid recommender combining multiple criteria, a self-healing mechanism using Large Language Model (LLM)-based error interpretation and adaptive learning from execution history. The approach is evaluated on 150 ML tasks across diverse scenarios. The system achieves an 84.7% end-to-end pipeline success rate, outperforming baseline methods. It demonstrates improved robustness through self-healing and reduces workflow development time compared to manual construction. The study introduces a novel integration of code-grounded RAG, explainable recommendation, self-healing execution and adaptive learning within a single architecture, showing that tightly coupled intelligent components can outperform isolated solutions.
title Think it, Run it: Autonomous ML pipeline generation via self-healing multi-agent AI
topic Artificial Intelligence
url https://arxiv.org/abs/2604.27096