A Collaborative Multi-Agent Approach to Retrieval-Augmented Generation Across Diverse Data
Aniruddha Salve, Saba Attar, Mahesh Deshmukh, Sayali Shivpuje, Arnab Mitra Utsab
TL;DR
The paper tackles the challenge of enabling LLMs to reliably incorporate dynamic and private data from diverse sources by extending Retrieval-Augmented Generation into a Multi-Agent framework. It proposes specialized agents for relational, document, and graph databases, a centralized query-execution environment, and a generative component that synthesizes final responses, with explicit formulations such as $Q_{ ext{generated}} = f_{ ext{agent}}(Q_{ ext{user}}, S_{ ext{schema}})$, $R_{ ext{query}} = g_{ ext{db}}(Q_{ ext{generated}}, D_{ ext{connection}})$, and $A_{ ext{response}} = h_{ ext{gen}}(Q_{ ext{user}}, R_{ ext{query}})$. Key contributions include specialized database agents (MySQL, MongoDB, Neo4j, ElasticSearch), centralized query execution to unify heterogeneous outputs, collaborative agent workflows, thoughtful integration with generative AI, and strategies to reduce token overhead while maintaining accuracy and scalability across industries. The work lays a foundation for robust, efficient, and adaptable generative-analytics pipelines in polyglot data environments, with practical implications for healthcare, finance, logistics, and beyond. By formalizing agent specialization and a modular execution layer, the approach enables future research in multi-agent coordination, adaptive prompting, and scalable deployment in dynamic data landscapes.
Abstract
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external, domain-specific data into the generative process. While LLMs are highly capable, they often rely on static, pre-trained datasets, limiting their ability to integrate dynamic or private data. Traditional RAG systems typically use a single-agent architecture to handle query generation, data retrieval, and response synthesis. However, this approach becomes inefficient when dealing with diverse data sources, such as relational databases, document stores, and graph databases, often leading to performance bottlenecks and reduced accuracy. This paper proposes a multi-agent RAG system to address these limitations. Specialized agents, each optimized for a specific data source, handle query generation for relational, NoSQL, and document-based systems. These agents collaborate within a modular framework, with query execution delegated to an environment designed for compatibility across various database types. This distributed approach enhances query efficiency, reduces token overhead, and improves response accuracy by ensuring that each agent focuses on its specialized task. The proposed system is scalable and adaptable, making it ideal for generative AI workflows that require integration with diverse, dynamic, or private data sources. By leveraging specialized agents and a modular execution environment, the system provides an efficient and robust solution for handling complex, heterogeneous data environments in generative AI applications.