This Systematic Literature Review examines prompt engineering in automatic code generation using large language models (LLMs) and shows that prompt engineering has been established as a key discipline for optimizing interaction with LLMs and improve the accuracy, robustness, and applicability of the generated code.
This systematic review presents an analysis of the "Vibe Coding" methodology — a contemporary approach to the iterative software development process using Large Language Models (LLMs). Code generation tools are transforming software development by enabling programmers to formulate tasks and describe the desired behavior of software in natural language, while LLMs generate source code corresponding to these requests. The review systematizes current methodologies for the use of LLMs, highlights application examples, evaluates the effectiveness of generated code, discusses emerging challenges, and outlines future development trends of the technology. The aim of this work is to provide a comprehensive understanding of the capabilities and limitations of Vibe Coding as a transformational methodology in software engineering.
A. Dzhonov, S. M. Avdoshin· INFORMACIONNYE TEHNOLOGII· 0 citations
Prompt engineering is increasingly embedded in software development practice, yet software engineering curricula lack evidence-grounded guidance on which prompt-related competencies to prioritize and how to assess them. This paper presents a large-scale empirical triangulation of industry demand and curricular supply for prompt-engineering competencies in software development. By analysing prompt-related job advertisements across major economies and auditing course descriptions from leading computer science programs, we identify systematic mismatches between practice-facing expectations and formal educational coverage. Industry demand consistently emphasizes prompt design alongside evaluation and testing, with strong signals for prompt optimization and a substantial subset of postings highlighting retrieval augmentation and orchestration. In contrast, university curricula predominantly foreground prompt creation and refinement, with limited explicit emphasis on systematic evaluation. Building on this triangulated evidence, we distil three recurring gaps and derive assessment-oriented implications, specifying inspectable student artefacts, such as evaluation harnesses, lifecycle documentation, and safety testing evidence, that allow prompt-engineering competence to be evaluated in software engineering terms. Collectively, the study provides an empirical foundation to inform curriculum design and assessment in software engineering education amid the rapid diffusion of large language models.
Current research is summarized to identify key gaps and future directions to optimize LLM based APR are proposed, to assure its reliability and scalability in real world software development.
Fatmaelzahra Hamdi, Ramadam Moawad, A. Mohsen· Journal of universal compute...· 0 citations
Prompt engineering has emerged as a critical yet undertaught skill for software developers, one that traditional learning approaches are ill-equipped to support given its evolving, interactive, and context-dependent nature. In this paper, we introduce Prompt Coach (PC), an agentic tutor that helps developers learn how to craft high-quality code-generation prompts through Socratic guidance embedded in-flow within their IDE. PC evaluates prompt quality across multiple dimensions and surfaces targeted questions to guide self-correction, grounded in the developer's codebase and the behavior of the target LLM. We present an early empirical study with 15 professional developers combining quantitative prompt quality scoring with qualitative perception measures. Participants showed statistically significant improvements after a single 60-minute session, with the largest gains across dimensions commonly overlooked by developers. They also reported strong trust, high adoption readiness, and unanimous agreement that PC improved their prompt-writing skills.
Rohit Mehra, Kapil Singi, Vikrant S. Kaulgud et al.· 0 citations
A large-scale empirical study of mainstream open-source agent frameworks from an engineering perspective, providing empirical evidence linking framework design choices to engineering risks and highlighting the need for stronger guidance and support in agent framework development.
Yibo Zhai, Junjun Si, Yan Wang et al.· SIGSOFT FSE Companion· 0 citations
Algorithm-Driven Development is introduced, a methodology developed from industrial practice to address recurring challenges in translating requirements into reliable, testable, and maintainable software behavior that provides systematic coverage of functional scenarios from the outset of development.
Philippe Jawish, Pierre Evrard, Alexandre Lemerle et al.· Journal of Systems and Softw...· 0 citations