The restrictions imposed by the COVID-19 pandemic required software development teams to adapt, being forced to work remotely and adjust the software engineering activities accordingly. In the studies evaluating these effects, a few have assessed the impact on software engineering activities from a broader perspective and after a period of time when teams had time to adjust to the changes. No studies have been found comparing software startups and established companies either. This paper aims to investigate the impacts of COVID-19 on software development activities after one year of the pandemic restrictions, comparing the results between startups and established companies. Our approach was to design a cross-sectional survey and distribute it online among software development companies worldwide. The participants were asked about their perception of COVID-19’s pandemic impact on different software engineering activities: requirements engineering, software architecture, user experience design, software implementation, and software quality assurance. The survey received 170 valid answers from 29 countries, and for all the software engineering activities, we found that most respondents did not observe a significant impact. The results also showed that software startups and established companies were affected differently since, in some activities, we found a negative impact in the former and a positive impact in the latter. Regarding the time spent on each software engineering activity, most of the answers reported no change, but on those that did, the result points to an increase in time. Thus, we cannot find any relation between the change in time of effort and the reported positive or negative impact.
Hosna Hooshyar, E. Guerra, Jorge Melegati et al.· IEEE Access· 4 citations
Large Language Models (LLMs) are integrated into software systems and AI services, making efficient LLM serving a concern for software engineering. Serving LLMs is challenging because inference requires computation, memory, GPU resources, and execution while maintaining latency and throughput. Although prior research has proposed LLM inference, optimization, and serving techniques and frameworks, little is known about how they are adopted in practice. In this study, we investigate the use of LLM serving frameworks and serving methods in open-source software systems. We identify and analyze five LLM-specific frameworks: vLLM, SGLang, TensorRT-LLM, LMDeploy, and FlashInfer. We examine how these frameworks and techniques are adopted individually and in combination, how adoption varies across categories of LLMs, and how repositories differ in intent, focus, use case, and architectural design. Our results show that vLLM is the most visible framework in popularity and adoption, while parallel computation, memory management, and network pruning are the most frequently used serving-method categories. Multi-framework usage is limited, suggesting that developers rely on a single serving framework; however, combined frameworks connect complementary capabilities across the serving stack. Framework adoption varies across model families, modalities, model sizes, domain specializations, and deployment settings. Repository-level analysis shows that LLM serving frameworks support applications and architectures, including Reinforcement Learning (RL)-based reasoning, multimodal generation and understanding, microservices, and cloud infrastructure. Overall, this study provides a large-scale empirical characterization of LLM serving framework adoption in practice and offers insights for researchers, framework maintainers, and practitioners working on LLM systems.
Forough Majidi, Mohammad Mehdi Morovati, F. Khomh et al.· 0 citations
Large-scale human–agent collaboration is investigated by comparing 40,214 pull requests across 2,807 GitHub repositories, including 33,596 agent-authored PRs from five autonomous coding agents and 6,618 human-authored PRs, revealing a socio-technical trade-off.
A. Njoku, Zohreh Sharafi, F. Khomh· AIware· 2 citations
This study characterize agentic pull requests (PR) in comparison to human generated PRs and to examine how their properties change across different stages of the development lifecycle, offering a more nuanced understanding of their benefits and limitations in real-world practices.
Iren Mazloomzadeh, Mohammad Mehdi Morovati, F. Khomh· 0 citations