Model-Assisted and Human-Guided: Perceptions and Practices of Software Professionals Using LLMs for Coding

TL;DR

This paper investigates how software professionals use large language models (LLMs) for coding and their perceptions of these tools. Using a global cross-sectional survey of 131 practitioners, the study reveals that LLMs primarily serve as assistive aids—facilitating code generation, debugging support, learning, and testing—while practitioners modify, verify, or augment outputs rather than deploying them wholesale. Participants report productivity gains and learning benefits but express concerns about inaccuracies, limited context, and ethical risks, maintaining cautious, human-in-the-loop practices for production code. The findings offer practitioner-centered insights for designing responsible LLM-enabled development workflows and point to future research on trust dynamics, prompting strategies, and domain-specific guidelines. Overall, the work provides a grounded understanding of current LLM adoption in software engineering and emphasizes the need for thoughtful integration that preserves human oversight and accountability.

Abstract

Large Language Models have quickly become a central component of modern software development workflows, and software practitioners are increasingly integrating LLMs into various stages of the software development lifecycle. Despite the growing presence of LLMs, there is still a limited understanding of how these tools are actually used in practice and how professionals perceive their benefits and limitations. This paper presents preliminary findings from a global survey of 131 software practitioners. Our results reveal how LLMs are utilized for various coding-specific tasks. Software professionals report benefits such as increased productivity, reduced cognitive load, and faster learning, but also raise concerns about LLMs' inaccurate outputs, limited context awareness, and associated ethical risks. Most developers treat LLMs as assistive tools rather than standalone solutions, reflecting a cautious yet practical approach to their integration. Our findings provide an early, practitioner-focused perspective on LLM adoption, highlighting key considerations for future research and responsible use in software engineering.