Researchers have developed a multi-AI agent model for conducting systematic literature reviews (SLRs) that fully automatize the process, harnessing the capabilities of Large Language Models (LLMs).

Summary:

• The model offers a user-friendly interface where researchers input their topic and receive a search string for retrieving papers.
• It implements an inclusive and exclusive filtering process, summarizing abstracts to focus on the most relevant studies.
• The final phase involves a thorough analysis of the papers concerning predefined research questions.
• The model has been positively evaluated by software engineering researchers who provided constructive feedback.

Importance:

This AI-powered approach to SLRs could significantly reduce the manual effort required in evidence-based research, leading to faster and more reliable outcomes. It presents an exciting opportunity for further development and integration into various research fields, potentially revolutionizing the way literature reviews are conducted.