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{204713,
        author = {Aswin Deivanayagam Subramanian and Parivel N and Varunesh S and Dr. N Revathi},
        title = {AI Agents for Drug Repurposing: A Multi-Agent Framework for Biomedical Reasoning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {4327-4351},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204713},
        abstract = {This project proposes an intelligent multi-agent system for drug repurposing that leverages Retrieval Augmented Generation (RAG), Large Language Models (LLMs), semantic vector databases, and collaborative AI agents to identify potential new therapeutic applications for existing drugs. The system is developed using FastAPI, LangGraph, Qdrant, Ollama (Llama 3), and the all-MiniLM-L6-v2 embedding model. Specialized agents, including Literature, Clinical, Patent, and Safety Agents, collaboratively analyse biomedical evidence obtained from PubMed, ClinicalTrials.gov, DrugBank, and patent repositories. A governance-based validation mechanism evaluates agent outputs, assigns confidence scores, and reduces hallucinations to improve reliability and explainability. Experimental observations demonstrated effective semantic retrieval, evidence-grounded reasoning, and improved decision support for drug repurposing research. By supporting data-driven healthcare innovation and evidence-based biomedical discovery, the proposed system contributes towards Sustainable Development Goal 3 (Good Health and Well-Being), with future scope for real-time clinical integration, advanced biomedical reasoning, and large-scale pharmaceutical applications.},
        keywords = {},
        month = {June},
        }