A Systematic Literature Review of the Use of GenAI Assistants for Code Comprehension: Implications for Computing Education Research and Practice

TL;DR

GenAI assistants offer promising avenues to support code comprehension through explanations, pedagogy, and documentation, but their outputs can be inaccurate and context-sensitive. The authors conducted an SLR of 31 studies (2022–2024), classifying five core approaches and detailing methods and effectiveness, with lab-based studies predominating. Key findings show improved understanding and productivity in several contexts, particularly for professionals, while highlighting persistent issues like hallucinations and prompt-sensitivity that call for hybrid human–AI workflows. The work provides practical implications for students, instructors, researchers, and tool developers and calls for standardized metrics and longitudinal evaluations to advance computing education and practice.

Abstract

The ability to comprehend code has long been recognized as an essential skill in software engineering. As programmers lean more heavily on generative artificial intelligence (GenAI) assistants to develop code solutions, it is becoming increasingly important for programmers to comprehend GenAI solutions so that they can verify their appropriateness and properly integrate them into existing code. At the same time, GenAI tools are increasingly being enlisted to provide programmers with tailored explanations of code written both by GenAI and humans. Thus, in computing education, GenAI presents new challenges and opportunities for learners who are trying to comprehend computer programs. To provide computing educators with evidence-based guidance on the use of GenAI to facilitate code comprehension and to identify directions for future research, we present a systematic literature review (SLR) of state-of-the-art approaches and tools that leverage GenAI to enhance code comprehension. Our SLR focuses on 31 studies published between 2022 and 2024. Despite their potential, GenAI assistants often yield inaccurate or unclear explanations, and novice programmers frequently struggle to craft effective prompts, thereby impeding their ability to leverage GenAI to aid code comprehension. Our review classifies GenAI-based approaches and tools, identifies methods used to study them, and summarizes the empirical evaluations of their effectiveness. We consider the implications of our findings for computing education research and practice, and identify directions for future research.

Figures (8)

• Figure 1: SLR Methodology
• Figure 2: Number of papers published by year
• Figure 3: Number of papers published by conference/journal
• Figure 4: Counts of Category Items
• Figure 5: Approaches to enhancing code comprehension using GenAI. Number of papers categorized into each approach is shown in parentheses.