Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{202409,
        author = {Ananya Jha and Dr. Asha T and Dr. Maya B S and Akshit Mehta and Khushi Gupta and Manpreet Kaur},
        title = {A Multi-Agent AI Framework for Unified Healthcare Assistance Using Retrieval Augmented Generation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {8856-8863},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202409},
        abstract = {This paper proposes a centralized AI system for healthcare assistance that uses a manager agent to orchestrate three specialized agents: a Diagnostics Agent, a Search Agent, and a Hospital Operations Agent. The Diagnostics Agent employs a fine-tuned clinical BERT model (BioClinicalBERT) combined with Retrieval-Augmented Generation (RAG) over a ChromaDB vector store, enriched by results from a Search Agent. The Search Agent integrates Google Custom Search on trusted medical sites and an internal document RAG system. The Hospital Operations Agent uses Python-based analytics and visualization tools to present patient and resource data, aiding junior doctors with on-demand preliminary diagnostics. This modular, RAG- driven approach is compared against monolithic Large Language Models (LLMs) and fine-tuned models, demonstrating improved efficiency, accuracy, and cost-effectiveness. The orchestration of specialized agents not only parallelizes complex tasks but also mitigates hallucinations through domain-focused retrieval. Comparative tables and scenarios highlight these benefits, un- derscoring how modular RAG architectures can adapt rapidly to new medical information without costly retraining.},
        keywords = {Multi-agent systems, RAG, LLM, BERT, Clin- ical decision support, Healthcare AI, Agent Orchestration, Evidence-Based diagnosis, Hospital Operations Analytics, Knowl- edge Retrieval.},
        month = {May},
        }