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.

翻译：大数据即服务(BDaaS)平台需要在数据摄取、清洗、特征工程、模型开发、部署及部署后监控等全流程实现可靠自动化。然而，现有基于大语言模型(LLM)的数据科学智能体与AutoML系统主要聚焦于孤立工作流阶段，对生命周期级编排、工件治理、人工监督及漂移感知自适应能力支持有限。本文提出一种基于LLM编排多智能体协作的可信自组装BDaaS框架。所提架构将BDaaS生命周期分解为数据摄取、数据清洗、特征工程、AutoML训练、模型评估、MLOps部署、监控及漂移检测等专业化智能体。中心LLM编排层负责协调智能体执行、验证中间输出、管理工作流上下文并支持动态工作流组合。该框架还集成共享工件治理、可复现性支持、人在回路检查点及漂移感知反馈回路。采用含缺失值、分类变量、异常值、类别不平衡及模拟协变量漂移的受控表格基准数据集进行原型评估。与手动ML、仅AutoML及单智能体LLM基线相比，所提多智能体BDaaS流水线在保持竞争性预测性能的同时，显著提升生命周期级可靠性，包括工作流完成度、工件可追溯性、部署就绪性、可复现性及漂移恢复能力。结果表明，LLM编排的多智能体系统可将传统AutoML扩展至可信、自适应且面向生产的BDaaS生命周期自动化。