The traditional approach to conducting systematic literature reviews (SLRs) has been labor-intensive and time-consuming. A new multi-AI agent model tackles this issue, utilizing Large Language Models (LLMs) to automate the SLR process. This user-friendly system accepts research topics, autonomously retrieves academic papers, summarizes abstracts, and conducts detailed analyses.

Empirical Evaluation Highlights:

• SLR automation via multi-agent AI implementation
• Enhanced precision by focusing on titles within the specific research realm
• Abstract summarization and paper analysis geared towards predefined questions
• GitHub repository available for the research community

The significance of this research lies in its potential to revolutionize how SLRs are conducted, freeing researchers to focus on interpretation and analysis rather than data collection. Furthermore, this system could be a precursor to broader applications in academic research, making it a noteworthy advancement for scholars across various fields.