Enhancing Systematic Literature Reviews: Evaluating the Performance of LLM-Based Tools Across Key Systematic Literature Review Stages

AI-based tools are reshaping systematic literature reviews (SLRs), offering transformative capabilities in literature retrieval, research visualization, and summarization. This research evaluates the performance of platforms such as SciSpace, Elicit, ResearchRabbit, Scite.ai, Consensus, Claude.ai, ChatGPT, Google Gemini, Perplexity, and Microsoft Co-Pilot across the key stages of SLRs—planning, conducting, and reporting. While these tools significantly enhance workflow efficiency and accuracy, challenges remain, including variability in result quality, limited access to advanced features in free-tier versions, and the necessity for human oversight to validate outputs. To address these challenges, this research introduces guidelines for effectively integrating AI tools into SLR processes, emphasizing hybrid workflows that combine AI efficiency with human expertise. The findings underscore the potential of AI to streamline SLRs while highlighting the importance of addressing tool limitations and ensuring adherence to academic and ethical standards. Future work should expand into interdisciplinary research, explore comparisons with traditional methodologies, and validate proposed best practices to further harness LLM’s potential in advancing systematic reviews across diverse research domains.