Understanding the Role of Large Language Models in Software Engineering: Evidence from an Industry Survey

• URL: http://arxiv.org/abs/2512.21347v1
• Date: Fri, 19 Dec 2025 20:57:19 GMT
• Title: Understanding the Role of Large Language Models in Software Engineering: Evidence from an Industry Survey
• Authors: Vítor Mateus de Brito, Kleinner Farias,
• Abstract summary: This paper reports an empirical study of Large Language Models (LLMs) adoption in software engineering, based on a survey of 46 industry professionals.<n>Results reveal positive perceptions of LLMs, particularly regarding faster resolution of technical questions, improved documentation support, and enhanced source code standardization.<n> respondents also expressed concerns about cognitive dependence, security risks, and the potential erosion of technical autonomy.
• Score: 0.6660458629649825
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Coding With AI: From a Reflection on Industrial Practices to Future Computer Science and Software Engineering Education [1.5516092077598485]
  Recent advances in large language models (LLMs) have introduced new paradigms in software development.<n>This paper investigates how LLM coding tools are used in professional practice, associated concerns and risks, and the resulting transformations in development.<n>Building on these insights, we argue for curricular shifts toward problem-solving, architectural thinking, code review, and early project-based learning.
  arXiv  Detail & Related papers  (2025-12-30T04:39:59Z)
• From Code Foundation Models to Agents and Applications: A Practical Guide to Code Intelligence [150.3696990310269]
  Large language models (LLMs) have transformed automated software development by enabling direct translation of natural language descriptions into functional code.<n>We provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs.<n>We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder)
  arXiv  Detail & Related papers  (2025-11-23T17:09:34Z)
• Model-Assisted and Human-Guided: Perceptions and Practices of Software Professionals Using LLMs for Coding [2.198430261120653]
  Large Language Models have quickly become a central component of modern software development.<n>This paper presents preliminary findings from a global survey of 131 software practitioners.
  arXiv  Detail & Related papers  (2025-10-10T06:59:56Z)
• Using LLMs and Essence to Support Software Practice Adoption [0.3609538870261841]
  This study explores the integration of Essence, a standard and thinking framework for managing software engineering practices, with large language models (LLMs)<n>The proposed system consistently outperforms its baseline counterpart in domain-specific tasks.
  arXiv  Detail & Related papers  (2025-08-22T14:59:35Z)
• Evaluating Large Language Models for Real-World Engineering Tasks [75.97299249823972]
  This paper introduces a curated database comprising over 100 questions derived from authentic, production-oriented engineering scenarios.<n>Using this dataset, we evaluate four state-of-the-art Large Language Models (LLMs)<n>Our results show that LLMs demonstrate strengths in basic temporal and structural reasoning but struggle significantly with abstract reasoning, formal modeling, and context-sensitive engineering logic.
  arXiv  Detail & Related papers  (2025-05-12T14:05:23Z)
• LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early Adopters [3.4069804433026314]
  Large language models (LLMs) like OpenAI ChatGPT, Google Gemini, and GitHub Copilot are rapidly gaining traction in the software industry.<n>Our study provides a nuanced understanding of how LLMs are shaping the landscape of software development.
  arXiv  Detail & Related papers  (2025-03-06T22:27:05Z)
• LLM Post-Training: A Deep Dive into Reasoning Large Language Models [131.10969986056]
  Large Language Models (LLMs) have transformed the natural language processing landscape and brought to life diverse applications.<n>Post-training methods enable LLMs to refine their knowledge, improve reasoning, enhance factual accuracy, and align more effectively with user intents and ethical considerations.
  arXiv  Detail & Related papers  (2025-02-28T18:59:54Z)
• An Overview of Large Language Models for Statisticians [109.38601458831545]
  Large Language Models (LLMs) have emerged as transformative tools in artificial intelligence (AI)<n>This paper explores potential areas where statisticians can make important contributions to the development of LLMs.<n>We focus on issues such as uncertainty quantification, interpretability, fairness, privacy, watermarking and model adaptation.
  arXiv  Detail & Related papers  (2025-02-25T03:40:36Z)
• Large Language Models for Code Generation: The Practitioners Perspective [4.946128083535776]
  Large Language Models (LLMs) have emerged as coding assistants, capable of generating source code from natural language prompts.<n>We propose and develop a multi-model unified platform to generate and execute code based on natural language prompts.<n>We conducted a survey with 60 software practitioners from 11 countries across four continents to evaluate the usability, performance, strengths, and limitations of each model.
  arXiv  Detail & Related papers  (2025-01-28T14:52:16Z)
• Exploring the Evidence-Based SE Beliefs of Generative AI Tools [2.3480418671346164]
  We investigate the "beliefs" of generative AI tools increasingly used to support software development in practice.<n>Our findings demonstrate generative AI tools have ambiguous beliefs regarding research claims and lack credible evidence to support responses.
  arXiv  Detail & Related papers  (2024-07-18T21:06:39Z)
• Instruction Tuning for Large Language Models: A Survey [52.86322823501338]
  We make a systematic review of the literature, including the general methodology of supervised fine-tuning (SFT)<n>We also review the potential pitfalls of SFT along with criticism against it, along with efforts pointing out current deficiencies of existing strategies.
  arXiv  Detail & Related papers  (2023-08-21T15:35:16Z)
• Technology Readiness Levels for Machine Learning Systems [107.56979560568232]
  Development and deployment of machine learning systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. We have developed a proven systems engineering approach for machine learning development and deployment. Our "Machine Learning Technology Readiness Levels" framework defines a principled process to ensure robust, reliable, and responsible systems.
  arXiv  Detail & Related papers  (2021-01-11T15:54:48Z)
• Technology Readiness Levels for AI & ML [79.22051549519989]
  Development of machine learning systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. Engineering systems follow well-defined processes and testing standards to streamline development for high-quality, reliable results. We propose a proven systems engineering approach for machine learning development and deployment.
  arXiv  Detail & Related papers  (2020-06-21T17:14:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.