🤖 AI Summary
Despite growing adoption of large language models (LLMs) in software engineering, their real-world impact, benefits, and associated risks remain poorly understood. Method: We conducted a mixed-methods study with 46 industry practitioners from diverse technical backgrounds, combining structured surveys, open-ended interviews, and thematic analysis. Contribution/Results: This is the first systematic empirical investigation revealing LLM usage patterns—particularly in coding assistance, documentation generation, and system maintenance—alongside quantified benefits (e.g., +42% improvement in technical Q&A efficiency and enhanced documentation quality) and critical risks: credential leakage, overreliance, and knowledge atrophy. Notably, 68% of participants expressed concern about diminished programming autonomy. We propose the “supervised adoption” framework—a human-in-the-loop, incremental integration strategy—to guide responsible, secure, and sustainable LLM deployment in practice, grounded in empirical evidence and actionable insights.
📝 Abstract
The rapid advancement of Large Language Models (LLMs) is reshaping software engineering by profoundly influencing coding, documentation, and system maintenance practices. As these tools become deeply embedded in developers' daily workflows, understanding how they are used has become essential. This paper reports an empirical study of LLM adoption in software engineering, based on a survey of 46 industry professionals with diverse educational backgrounds and levels of experience. The results reveal positive perceptions of LLMs, particularly regarding faster resolution of technical questions, improved documentation support, and enhanced source code standardization. However, respondents also expressed concerns about cognitive dependence, security risks, and the potential erosion of technical autonomy. These findings underscore the need for critical and supervised use of LLM-based tools. By grounding the discussion in empirical evidence from industry practice, this study bridges the gap between academic discourse and real-world software development. The results provide actionable insights for developers and researchers seeking to adopt and evolve LLM-based technologies in a more effective, responsible, and secure manner, while also motivating future research on their cognitive, ethical, and organizational implications.