SLRMentor: An LLM-Based Tool Supporting Learning of SLR in Software Engineering

2026-06-05

AI Summary

This study addresses the high entry barrier faced by novice software engineering researchers in conducting systematic literature reviews (SLRs) by proposing the first large language model (LLM)-based conversational assistance tool. Integrating a knowledge base of established SLR methodologies with natural language interaction capabilities, the tool supports core planning tasks such as constructing search strings and formulating inclusion and exclusion criteria, while providing justifications grounded in authoritative guidelines. By innovatively leveraging LLMs to support both SLR education and practical execution, the approach maintains methodological rigor while preserving the user’s active role in critical decision-making. Preliminary evaluation demonstrates that the tool effectively clarifies SLR procedures and key judgment points, substantially reducing the learning curve for beginners.

Abstract

This paper presents SLRMentor, a conversational assistant designed to support both learning about the systematic literature review process and the execution of planning activities in software engineering. The tool offers general guidance on SLR methodology and supports key planning tasks, including search string construction and reasoning about inclusion and exclusion criteria, with explanations grounded in established SLR guidelines. A pilot validation with graduate students suggests that SLRMentor helps clarify the SLR process and planning decisions, lowers initial barriers for novice researchers, and supports learning while still requiring active methodological judgment.

Problem

• Systematic Literature Review
• Software Engineering
• Learning Support
• Novice Researchers
• SLR Planning

Innovation

• LLM-based tool
• Systematic Literature Review
• Conversational assistant
• Search string construction
• Inclusion/exclusion criteria