Vibe Coding in Software Development: A Multivocal Literature Review

Vibe Coding: Practice, Performance, Productivity, and Risk -A State-of-the-Art Review

This state-of-the-art review assembles that evidence across a cross-disciplinary corpus spanning software engineering, human-computer interaction, labour economics, security research, governance, and education, finding the early benchmarks saturated but task-level capability uneven.

A Systematic Analysis of AI-Assisted Vibe Coding in Software Development: Opportunities, Challenges, and Risks

The literature on vibe coding has grown rapidly; however, it remains fragmented and is largely dominated by industry reports, leaving its position relative to traditional manual programming and low-code development insufficiently examined. This gap makes it difficult for both researchers and practitioners to determine when vibe coding is appropriate and what risks should be anticipated. Purpose: This study aims to systematically map the current landscape of vibe coding, develop a comparative framework against manual and low-code software development approaches, and propose practical risk mitigation recommendations for software development practitioners. Methodology: A Systematic Literature Review (SLR) was conducted following the PRISMA protocol. Relevant publications from 2023 to 2026 were retrieved from IEEE Xplore, ACM Digital Library, Springer, ScienceDirect, and arXiv, resulting in 61 studies that were analyzed using thematic analysis. Findings: The results indicate that vibe coding can accelerate software prototyping by approximately 40–60% compared with manual development. However, it introduces a verification bottleneck by shifting developers' workload from code implementation to quality assurance and validation. Compared with low-code development, vibe coding provides greater flexibility in expressing user intent but exhibits lower output predictability. In comparison with manual development, it offers significant gains in development speed while sacrificing architectural control and code security, thereby increasing the risks of technical skill degradation, hidden security vulnerabilities, and accumulated technical debt. Implications: The findings provide practical guidance for software development teams in identifying project phases that are suitable for extensive adoption of vibe coding and those that still require manual architectural review. The study also emphasizes the importance of integrating security auditing and technical debt monitoring into AI-assisted software development workflows. Originality/Value: The novelty of this study lies in its explicit comparative framework, which systematically positions vibe coding alongside manual and low-code development across six technical dimensions, extending previous studies that have generally examined vibe coding in isolation.

Fragmented Markers, Mixed Results: A Systematic Review of AI Coding Assistants and Developer Productivity

Educational Research-Driven Software Development

Generative AI-assisted coding may have introduced a meaningful opportunity for educational researchers with no programming experience to extend their work beyond typical scholarly outputs by creating functional software. Translating research into applications has historically required significant coding expertise, but generative AI has lowered this barrier substantially. Proposed is educational research-driven development (ERDD), an emergent conceptual cross-disciplinary framework combining the educational research process with the software development lifecycle (SDLC) to produce executable scholarship deployable directly to stakeholders. A cross-disciplinary process comparison revealed similarities and differences between the two fields, producing a unified set of scholar-coder workflow steps and two researcher postures: the Sequential Posture, which concludes research before development begins, and the Integrated Posture, which runs both processes in deliberate tandem. Importantly, ERDD has not been validated with rigorous research, and its generalizability has yet to be established. An applied workflow example is demonstrated from the perspective of a non-technical scholar-coder producing a functional web application for educators to record student mental health observational data. The application is accessible at: https://mlittrell-ttu.github.io/mlittrell.github.io/mwb-tracker.html

AI-Conducted Interviews in Empirical Software Engineering: An Experience Report

Semi-structured interviews are widely used in empirical software engineering (ESE), but they are resource-intensive and difficult to coordinate across schedules, locations, and natural languages. This experience report examines a customized MyGPT used to conduct short, self-administered interviews in two ESE studies: one on refactoring practices and another on generative AI in Scrum-related activities. Participants accessed the interviewer through shared links, used voice interaction, selected a preferred natural language, and completed the interview without a researcher present. The AI followed a predefined protocol and generated a structured synthesis that participants voluntarily submitted; these artifacts were not treated as verbatim transcripts. We analyzed 66 submissions and questionnaire responses, and audited artifact format, language, length, and protocol consistency. Of the submitted artifacts, 92.4% followed the expected synthesis format, 65 were predominantly in Portuguese and one in English, and two conflicted with the reported protocol. Participants generally rated the experience positively: 90.9% reported a positive overall experience and comfort, 95.5% considered the questions clear, 97.0% rated the pace positively, and 89.4% would participate again. Reported limitations included generic questions, limited sensitivity to answers, insufficient depth, privacy concerns, and missed human interaction. The findings support the operational viability and acceptability of this workflow among analyzed respondents, but do not establish completion rates, time savings, summary fidelity, or equivalence to human-conducted interviews. AI interviewers should therefore be treated as a complementary option for short, focused, low-risk studies, with protocol design, privacy guidance, artifact validation, and human oversight.

Code Refinement with Repository Context: How Far are We?

A high-quality benchmark of 1,000 code refinement instances from 328 Python, Java, and JavaScript repositories that focused on one of the most challenging code refinement scenarios that strictly requires repository-level knowledge reasoning, and a straightforward method, RepoRefiner, which retrieves repository-level context by collecting the full file content, extracting definitions of its identifiers, and summarizing these contexts to support code refinement.