LLM-Orchestrated Multi-Agent System Enhances BDaaS Lifecycle Automation

By PulseAugur Editorial · [2 sources] · 2026-06-16 13:34

Researchers have developed a novel Big-Data-as-a-Service (BDaaS) framework that utilizes LLM-orchestrated multi-agent collaboration for automated data engineering and MLOps. This framework decomposes the BDaaS lifecycle into specialized agents for tasks like data ingestion, cleaning, feature engineering, AutoML training, deployment, and monitoring. Evaluations on benchmark datasets demonstrated that the proposed multi-agent system achieves competitive predictive performance while enhancing lifecycle reliability, including artifact traceability and drift recovery, compared to manual ML, AutoML-only, and single-agent LLM baselines. AI

IMPACT This framework could streamline and improve the reliability of complex data engineering and MLOps workflows.

RANK_REASON The cluster contains an academic paper detailing a new framework and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.MA (Multiagent) →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

arXiv cs.AI TIER_1 English(EN) · Aueaphum Aueawatthanaphisut, Badri Raj Lamichhane · 2026-06-17 04:00

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

arXiv:2606.17915v1 Announce Type: cross Abstract: 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 ag…
arXiv cs.MA (Multiagent) TIER_1 English(EN) · Badri Raj Lamichhane · 2026-06-16 13:34

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

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 w…

COVERAGE [2]

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

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

RELATED ENTITIES

RELATED TOPICS