Systematic Literature Reviews (SLRs) are foundational for evidence-based research but are often labor-intensive. A novel solution discussed in ‘System for systematic literature review using multiple AI agents: Concept and an empirical evaluation’ (Read the full paper here) aims to change this by facilitating a fully automated SLR process with the help of AI agents and LLMs.

The proposed model improves the SLR process with a user-friendly interface for researchers to input topics, which is followed by the retrieval, summarization, and analysis of relevant papers based on research questions. The model was tested by software engineering researchers, who expressed high satisfaction, suggesting a significant step forward in automating literature reviews.

Key Insights:

• Introduction of a multi-AI agent model that enhances SLR efficiency and accuracy.
• Automation of the entire SLR process from generation of search strings to paper analysis.
• User-configurable process, allowing for specific inclusion and exclusion criteria.
• Positive feedback from software engineering researchers, indicating the model’s potential impact.

The potential for AI to assist with SLRs promises to reduce time and effort in research while ensuring quality and focus, opening avenues for more comprehensive and up-to-date literature analysis.