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{189779,
        author = {Vaibhav Hingnekar and Shrutkirti Kadam and Rehan George Varghese and Niteshkrishna Iyengar},
        title = {The Second Mind: Multi-Agent AI Research Assistant},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {163-169},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189779},
        abstract = {The exponential growth of academic literature challenges researchers in information discovery and knowledge syn- thesis. This paper presents Second Mind AI, a novel multi-agent framework that functions as an intelligent research assistant using Retrieval-Augmented Generation (RAG). The system combines Large Language Models with real-time data from the Semantic Scholar API through a unique two-phase iterative refinement mechanism. Our empirical evaluation against manual search and general- purpose LLMs shows that Second Mind AI reduces literature search time by 5.4 times (28.2 vs 152.5 seconds) while eliminating source hallucination entirely. The system maintains high relevance scores (4.3/5.0) with zero fabricated citations, validating its effectiveness for reliable academic research workflows.},
        keywords = {Academic Research Assistant, Iterative Refinement, Large Language Models, Multi-Agent Systems, Retrieval- Augmented Generation, Semantic Scholar.},
        month = {January},
        }