Copyright © 2025 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{180019,
        author = {Spoorthy G R and Smitha R and Punith Panduranga A B and Manas S Gowda and Dr. Madhu B R and Mr. S. Vinod Kumar},
        title = {Multi Agent Research Assistant},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {76-82},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180019},
        abstract = {In today’s knowledge economy, researchers face information overload due to the exponential growth of scientific publications. To address this, we introduce MARA (Multi-Agent Research Assistant)—an AI-powered tool that automates key stages of the research workflow. MARA uses a modular multi-agent system comprising Scholar, Critique, Synthesis, and Report agents. It retrieves the top five relevant papers from sources like arXiv, extracts key insights, evaluates contributions, identifies trends, and generates structured IEEE-style reports. Built with Streamlit and Flask, MARA offers a user-friendly interface and seamless backend integration.},
        keywords = {Multi-Agent Systems, Research Assistant, Literature Survey, IEEE Formatting, LLM Summarization, AI-Powered Tools, Virtual Research Assistant, NLP for Research, Research Automation.},
        month = {May},
        }