用大模型协调多个智能体，自动完成数据到部署的全流程管理。
Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization
- 大模型统筹多个专业智能体，分步完成数据清洗、建模、部署等任务。
- 在真实数据场景下，流程完成率和可复现性显著优于传统方法。
- 适合需要自动化、可追踪、抗数据漂移的生产级机器学习系统。
大数据即服务（BDaaS）平台需要在数据接入、清洗、特征工程、模型开发、部署及部署后监控等环节实现可靠自动化。然而现有基于大模型的数据科学代理和AutoML系统多聚焦于孤立流程阶段，缺乏对生命周期协同、成果治理、人工干预和漂移感知适应的支持。本文提出一种可信的自组合式BDaaS框架，采用大模型协调多智能体协作。该架构将BDaaS生命周期分解为数据接入、清洗、特征工程、AutoML训练、模型评估、MLOps部署、监控和漂移检测等专用智能体，由中心大模型协调执行、验证中间输出、管理上下文并支持动态流程组合。框架还集成共享成果治理、可复现性支持、人机协同检查点及漂移感知反馈回路。基于含缺失值、类别变量、异常值、类别不平衡和模拟协变量漂移的控制表格基准数据集进行原型评估。相比人工建模、仅AutoML及单智能体大模型基线，所提多智能体BDaaS流水线在预测性能相当的前提下，显著提升流程完成率、成果可追溯性、部署就绪度、可复现性和漂移恢复能力。结果表明，大模型协调的多智能体系统可将传统AutoML拓展为可信、自适应、面向生产的全生命周期自动化。
原文摘要 · Abstract (English)
Big-Data-as-a-Service (BDaaS) platforms require re liable automation across data ingestion, cleaning, feature engi neering, model development, deployment, and post-deployment monitoring. However, existing LLM-based data science agents and AutoML systems mainly focus on isolated workflow stages, leaving limited support for lifecycle-level orchestration, artifact governance, human oversight, and drift-aware adaptation. This paper proposes a trustworthy self-composable BDaaS frame work based on LLM-orchestrated multi-agent collaboration. The proposed architecture decomposes the BDaaS lifecycle into specialized agents for data ingestion, data cleaning, feature engineering, AutoML training, model evaluation, MLOps de ployment, monitoring, and drift detection. A central LLM or chestration layer coordinates agent execution, validates interme diate outputs, manages workflow context, and enables dynamic workflow composition. The framework also incorporates shared artifact governance, reproducibility support, human-in-the-loop checkpoints, and drift-aware feedback loops. A prototype-based evaluation is conducted using controlled tabular benchmark datasets with missing values, categorical variables, outliers, class imbalance, and simulated covariate drift. Compared with manual ML, AutoML-only, and single-agent LLM baselines, the pro posed multi-agent BDaaS pipeline achieves competitive predictive performance while improving lifecycle-level reliability, including workflow completion, artifact traceability, deployment readiness, reproducibility, and drift recovery. The results suggest that LLM-orchestrated multi-agent systems can extend conventional AutoML toward trustworthy, adaptive, and production-oriented BDaaS lifecycle automation.
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。