用五个智能代理自动构建机器学习流程，自修复且可解释。
Think it, Run it: Autonomous ML pipeline generation via self-healing multi-agent AI
- 五代理协同完成数据理解、目标解析、服务推荐、流程构建与执行。
- 在150个任务中实现84.7%的成功率，优于基线方法。
- 适合需要快速搭建可靠ML流程的研究者和工程师。
本文提出一种统一的多智能体架构，旨在从数据集和自然语言目标自动完成端到端机器学习（ML）流程生成，提升效率、鲁棒性和可解释性。该系统由五个智能体组成，分别负责数据探查、意图解析、微服务推荐、有向无环图（DAG）构建与执行。其整合了基于代码的检索增强生成（RAG）以理解微服务，一个结合多准则的可解释混合推荐器，以及基于大语言模型（LLM）的错误识别与执行历史自适应学习的自修复机制。在跨150个不同场景的ML任务上评估，系统达到84.7%的端到端流程成功率，优于基线方法，展现出更强的鲁棒性，并显著缩短流程开发时间。研究首次将基于代码的RAG、可解释推荐、自修复执行与自适应学习集成于单一架构中，表明紧密耦合的智能组件优于孤立方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。