A COMPREHENSIVE REVIEW ON AI DRIVEN LITERATURE RETRIEVAL-AUGMENTED REVIEW, GENERATION, KNOWLEDGE GRAPHS, AND RESEARCH GAP DETECTION

This review has provided a review of research foundations related to. Plus, the IRIS, an Intelligent Research & Information System for assisted literature review. In my experience, important developments in AI-assisted screening. Extraction, scientific NLP, semantic retrieval, RAG, self-reflective generation, agentic workflows, knowledge graphs, and graph-based corpus analysis are highlighted in this literature. Makes sense. Nonetheless, integration, evidence traceability, long-context handling, validation of research gaps, and standard evaluation are significant problems. These limitations have been overcome through the proposed IRIS. Has connected scholarly retrieval, scientific information extraction, evidence-grounded summarization, knowledge graph creation, agentic multi-step analysis, research gap identification. Citation aware report generation. Personally, because of this, rather than any specific novel component, the main. From where I stand, Contributions of the proposed system are its integration process and human-in-the-loop approach. To me, for a final year engineering project, the next step will be to develop. Evaluate a tangible system based on certain clear benchmarks. The way I see it, Then again, as long as the proposed system can highlight accurate retrieval, faithful summary creation, traceable citations, useful thematic relations. No kidding. Verified research gaps suggested, the IRIS will be able to offer an effective platform for literature review.

[1]  D. Scherbakov, N. Hubig, V. Jansari, A. Bakumenko, and L. A. Lenert, “The emergence of large language models as tools in literature reviews: A large language model-assisted systematic review,” Journal of the American Medical Informatics Association, vol. 32, no. 6, pp. 1071–1086, 2025, doi: 10.1093/jamia/ocaf063. [2] S. Agarwal, G. Sahu, A. Puri, I. H. Laradji, K. D. Dvijotham, J. Stanley, L. Charlin, and C. Pal, “LitLLMs, LLMs for Literature Review: Are We There Yet?,” Transactions on Machine Learning Research, 2025. [3]  J. L. Lieberum, M. Toews, M.-I. Metzendorf, F. Heilmeyer, W. Siemens, C. Haverkamp, D. Böhringer, J. J. Meerpohl, and A. Eisele-Metzger, “Large language models for conducting systematic reviews: On the rise, but not yet ready for use—a scoping review,” Journal of Clinical Epidemiology, vol. 181, art. 111746, 2025, doi: 10.1016/j.jclinepi.2025.111746. [4]  A. Singh, A. Ehtesham, S. Kumar, T. T. Khoei, and A. V. Vasilakos, “Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG,” arXiv:2501.09136, 2025. [5]  S. Guizani, T. Mazhar, T. Shahzad, W. Ahmad, A. Bibi, et al., “A systematic literature review to implement large language model in higher education: Issues and solutions,” Discover Education, vol. 4, art. 35, 2025, doi: 10.1007/s44217-025-00424-7. [6]  Y. Saleh, M. Abu Talib, Q. Nasir, and F. Dakalbab, “Evaluating large language models: A systematic review of efficiency, applications, and future directions,” Frontiers in Computer Science, vol. 7, 2025, doi: 10.3389/fcomp.2025.1523699. [7]  I. D. Mienye, N. Jere, G. Obaido, O. O. Ogunruku, and E. Esenogho, “Large language models: An overview of foundational architectures, recent trends, and a new taxonomy,” Discover Applied Sciences, vol. 7, art. 1027, 2025, doi: 10.1007/s42452-025-07668-w. [8]  F. Bolaños, A. Salatino, F. Osborne, and E. Motta, “Artificial intelligence for literature reviews: Opportunities and challenges,” Artificial Intelligence Review, vol. 57, art. 259, 2024, doi: 10.1007/s10462-024-10902-3. [9]  B. Han, T. Susnjak, and A. Mathrani, “Automating systematic literature reviews with retrieval-augmented generation: A comprehensive overview,” Applied Sciences, vol. 14, no. 19, art. 9103, 2024, doi: 10.3390/app14199103. [10] K. Choe, S. Park, S. Jung, H. Kim, J. W. Yang, H. Hong, and J. Seo, “Supporting novice researchers to write literature review using language models,” in Extended Abstracts of CHI 2024, 2024, pp. 1–9, doi: 10.1145/3613905.3650787.