Impact of LLMs on Team Collaboration in Software Development

TL;DR

This study updates the understanding of how Large Language Models affect team collaboration across the Software Development Life Cycle by combining literature review, two real-world case studies, and practitioner surveys through 2025. It finds that LLM-assisted tools improve efficiency, communication clarity, and cross-functional coordination, while also introducing challenges related to privacy, context accuracy, and potential over-reliance. The work analyzes self-collaboration and multi-agent frameworks, prompt engineering for team policies, and ideation support, showing concrete benefits such as faster task completion, automated documentation, and streamlined sprint reporting. It also outlines future directions—domain-specific customization, on-premises deployments, better tool integration, and robust trust and security measures—that will shape practical adoption and responsible deployment of AI-assisted software development teams.

Abstract

Large Language Models (LLMs) are increasingly being integrated into software development processes, with the potential to transform team workflows and productivity. This paper investigates how LLMs affect team collaboration throughout the Software Development Life Cycle (SDLC). We reframe and update a prior study with recent developments as of 2025, incorporating new literature and case studies. We outline the problem of collaboration hurdles in SDLC and explore how LLMs can enhance productivity, communication, and decision-making in a team context. Through literature review, industry examples, a team survey, and two case studies, we assess the impact of LLM-assisted tools (such as code generation assistants and AI-powered project management agents) on collaborative software engineering practices. Our findings indicate that LLMs can significantly improve efficiency (by automating repetitive tasks and documentation), enhance communication clarity, and aid cross-functional collaboration, while also introducing new challenges like model limitations and privacy concerns. We discuss these benefits and challenges, present research questions guiding the investigation, evaluate threats to validity, and suggest future research directions including domain-specific model customization, improved integration into development tools, and robust strategies for ensuring trust and security.