Software project management faces increasing demands as development practices evolve, motivating the development of new support tools. Recent advances in generative AI, particularly large language models (LLMs), offer opportunities to enhance project management by analysing project data and providing guidance using a natural-language interface. This paper presents a Design Science Research study that designs and implements a retrieval-augmented generation (RAG) chatbot integrated with an existing project monitoring tool for student software projects. The prototype validates the system architecture and evaluates prompt engineering using a commercial LLM. The results exhibit that project metrics can be effectively leveraged in a RAG chatbot to provide useful, context-aware assistance to project managers.

The use of Large Language Models (LLMs) for autonomous code generation is gaining attention in emerging technologies. As LLM capabilities expand, they offer new possibilities such as code refactoring, security enhancements, and legacy application upgrades. Many outdated web applications pose security and reliability challenges, yet companies continue using them due to the complexity and cost of upgrades. To address this, we propose an LLM-based multi-agent system that autonomously upgrades legacy web applications to the latest versions. The system distributes tasks across multiple phases, updating all relevant files. To evaluate its effectiveness, we employed Zero-Shot Learning (ZSL) and One-Shot Learning (OSL) prompts, applying identical instructions in both cases. The evaluation involved updating view files and measuring the number and types of errors in the output. For complex tasks, we counted the successfully met requirements. The experiments compared the proposed system with standalone LLM execution, repeated multiple times to account for stochastic behavior. Results indicate that our system maintains context across tasks and agents, improving solution quality over the base model in some cases. This study provides a foundation for future model implementations in legacy code updates. Additionally, findings highlight LLMs' ability to update small outdated files with high precision, even with basic prompts. The source code is publicly available on GitHub: https://github.com/alasalm1/Multi-agent-pipeline.

The growing need for scalable, maintainable, and fast-deploying systems has made microservice architecture widely popular in software development. This paper presents a system that uses Large Language Models (LLMs) to automate the API-first development of RESTful microservices. This system assists in creating OpenAPI specification, generating server code from it, and refining the code through a feedback loop that analyzes execution logs and error messages. By focusing on the API-first methodology, this system ensures that microservices are designed with well-defined interfaces, promoting consistency and reliability across the development life-cycle. The integration of log analysis enables the LLM to detect and address issues efficiently, reducing the number of iterations required to produce functional and robust services. This process automates the generation of microservices and also simplifies the debugging and refinement phases, allowing developers to focus on higher-level design and integration tasks. This system has the potential to benefit software developers, architects, and organizations to speed up software development cycles and reducing manual effort. To assess the potential of the system, we conducted surveys with six industry practitioners. After surveying practitioners, the system demonstrated notable advantages in enhancing development speed, automating repetitive tasks, and simplifying the prototyping process. While experienced developers appreciated its efficiency for specific tasks, some expressed concerns about its limitations in handling advanced customizations and larger-scale projects. The code is publicly available at https://github.com/sirbh/code-gen.

The integration of Large Language Models (LLMs) in Requirements Engineering (RE) education is reshaping pedagogical approaches, seeking to enhance student engagement and motivation while providing practical tools to support their professional future. This study empirically evaluates the impact of integrating LLMs in RE coursework. We examined how the guided use of LLMs influenced students’ learning experiences, and what benefits and challenges they perceived in using LLMs in RE practices. The study collected survey data from 179 students across two RE courses in two universities. LLMs were integrated into coursework through different instructional formats, i.e. individual assignments versus a team-based Agile project. Our findings indicate that LLMs improved students’ comprehension of RE concepts, particularly in tasks like requirements elicitation and documentation. However, students raised concerns about LLMs in education, including academic integrity, overreliance on AI, and challenges in integrating AI-generated content into assignments. Students who worked on individual assignments perceived that they benefited more than those who worked on team-based assignments, highlighting the importance of contextual AI integration. This study offers recommendations for the effective integration of LLMs in RE education. It proposes future research directions for balancing AI-assisted learning with critical thinking and collaborative practices in RE courses.

Abstract The lack of core theories is a challenge for the whole software engineering (SE) discipline, particularly crucial for the agile software development (ASD) field, which is largely practice-driven. Without solid and continuous theoretical development glued by core theories, ASD risks repeating wrong practices and oversimplifying real-world phenomena. To address this issue and foster a strong link between empirical evidence and theoretical development, we conduct this critical review using the Complex Network Analysis (CNA) approach, in response to the editors’ call on the XP2020 conference. Based on 83 selected articles and 88 identified theories, our analysis traced the originating disciplines of these theories and synthesized 3 key theory communities. We position ASD core theories between empirical generalization and middle-range theories in the SE theory spectrum and offer practical guidelines for researchers to use, borrow, and generate ASD theories. It is further recommended that new theory development be aligned with the theory of coordination and control theory while employing Complex Adaptive Systems (CAS) theory as a theoretical lens when borrowing theories to ASD.

ABSTRACT Context Generative artificial intelligence (GenAI) tools have become increasingly prevalent in software development, offering assistance to various managerial and technical project activities. Notable examples of these tools include OpenAI's ChatGPT, GitHub Copilot, and Amazon CodeWhisperer. Objective Although many recent publications have explored and evaluated the application of GenAI, a comprehensive understanding of the current development, applications, limitations, and open challenges remains unclear to many. Particularly, we do not have an overall picture of the current state of GenAI technology in practical software engineering usage scenarios. Method We conducted a literature review and focus groups for a duration of five months to develop a research agenda on GenAI for software engineering. Results We identified 78 open research questions (RQs) in 11 areas of software engineering. Our results show that it is possible to explore the adoption of GenAI in partial automation and support decision‐making in all software development activities. While the current literature is skewed toward software implementation, quality assurance and software maintenance, other areas, such as requirements engineering, software design, and software engineering education, would need further research attention. Common considerations when implementing GenAI include industry‐level assessment, dependability and accuracy, data accessibility, transparency, and sustainability aspects associated with the technology. Conclusions GenAI is bringing significant changes to the field of software engineering. Nevertheless, the state of research on the topic still remains immature. We believe that this research agenda holds significance and practical value for informing both researchers and practitioners about current applications and guiding future research.

In the era of 6G, developing and managing software requires cutting-edge software engineering (SE) theories and practices tailored for such complexity across a vast number of connected edge devices. Our project aims to lead the development of sustainable methods and energy-efficient orchestration models specifically for edge environments, enhancing architectural support driven by AI for contemporary edge-to-cloud continuum computing. This initiative seeks to position Finland at the forefront of the 6G landscape, focusing on sophisticated edge orchestration and robust software architectures to optimize the performance and scalability of edge networks. Collaborating with leading Finnish universities and companies, the project emphasizes deep industry-academia collaboration and international expertise to address critical challenges in edge orchestration and software architecture, aiming to drive significant advancements in software productivity and market impact.

Abstract In agile software development, maintaining high-quality user stories is crucial, but also challenging. This study explores the application of large language models (LLMs) to improve the quality of user stories within the agile teams of Austrian Post Group IT. We developed an Autonomous LLM-based Agent System (ALAS) and evaluated its impact on user story quality with 11 participants from six agile teams. Our findings reveal the potential of LLMs in improving user story quality, provide a practical example, and lay the foundation for future research into the broad application of LLMs in a variety of industry settings.

Open-source software (OSS) development has become increasingly influential in the software industry, promoting collaboration and knowledge sharing among developers and users. Along with rapidly evolving OSS projects, this paper explores requirements engineering (RE) practices and challenges through a systematic literature review (SLR). Synthesizing data from 43 selected papers, the study reports practices, techniques, and methods that assist RE activities in OSS projects, and also addresses challenges faced by practitioners and the potential solutions. The results of the literature review indicate a growing interest in using machine learning and statistical methods to assist RE activities, focusing on automated requirements identification and analysis using information from project discussion forums, issue reports, and other online resources. The findings also highlight the importance of community involvement, with many studies examining developers’ interaction patterns, expertise levels, and influence on projects. These findings provide valuable insights for OSS project managers and researchers, offering guidance on effectively handling requirements in OSS projects.

Software vulnerabilities play a major role, as there are multiple risks associated, including loss and manipulation of private data. The software engineering research community has been contributing to the body of knowledge by proposing several empirical studies on vulnerabilities and automated techniques to detect and remove them from source code. The reliability and generalizability of the findings heavily depend on the quality of the information mineable from publicly available datasets of vulnerabilities as well as on the availability and suitability of those databases. In this paper, we seek to understand the anatomy of the currently available vulnerability databases through a systematic mapping study where we analyze (1) what are the popular vulnerability databases adopted; (2) what are the goals for adoption; (3) what are the other sources of information adopted; (4) what are the methods and techniques; (5) which tools are proposed. An improved understanding of these aspects might not only allow researchers to take informed decisions on the databases to consider when doing research but also practitioners to establish reliable sources of information to inform their security policies and standards.

Open Source Software (OSS) is nowadays used and integrated in most of the commercial products. However, the selection of OSS projects for integration is not a simple process, mainly due to a of lack of clear selection models and lack of information from the OSS portals. We investigate the factors and metrics that practitioners currently consider when selecting OSS. We also investigate the source of information and portals that can be used to assess the factors, as well as the possibility to automatically extract such information with APIs. We elicited the factors and the metrics adopted to assess and compare OSS performing a survey among 23 experienced developers who often integrate OSS in the software they develop. Moreover, we investigated the APIs of the portals adopted to assess OSS extracting information for the most starred 100K projects in GitHub. We identified a set consisting of 8 main factors and 74 sub-factors, together with 170 related metrics that companies can use to select OSS to be integrated in their software projects. Unexpectedly, only a small part of the factors can be evaluated automatically, and out of 170 metrics, only 40 are available, of which only 22 returned information for all the 100K projects. Therefore, we recommend project maintainers and project repositories to pay attention to provide information for the project they are hosting, so as to increase the likelihood of being adopted. OSS selection can be partially automated, by extracting the information needed for the selection from portal APIs. OSS producers can benefit from our results by checking if they are providing all the information commonly required by potential adopters. Developers can benefit from our results, using the list of factors we selected as a checklist during the selection of OSS, or using the APIs we developed to automatically extract the data from OSS projects.

Open-source projects commonly receive new feature requests from different types of users from layperson end users to developers, who actively contribute code to the project. However, the submission of new feature requests and the processes adopted for handling them is not always clear. In this work, we aim at investigating the availability of the contribution information, and in particular on the new feature requests, on 66 out of the 100 most starred GitHub projects. We examined the contribution guidelines and other documentation from those 66 projects. We particularly searched for whether the projects openly welcomed new contributions, such as feature requests. Our finding shows that even the most starred GitHub projects are often not reporting information on how to contribute and, in particular, how new feature requests are managed.

The one-time pad (OTP) secure transmission relies on the random keys to achieve perfect secrecy, while the unpredictable wireless channel is shown to be a good random source. There is very few work of the joint design of OTP and key generation from wireless channels. This article provides a comprehensive and quantitative investigation on secure transmission achieved by OTP and wireless channel randomness. We propose two OTP secure transmission schemes, i.e., identical key-based physical-layer secure transmission (IK-PST) and un-IK-PST (UK-PST). We quantitatively analyze the performance of both schemes and prove that UK-PST outperforms IK-PST. We extend the pairwise schemes to a group of users in networks with star and chain topologies. We implement prototypes of both schemes and evaluate the proposed schemes through both simulations and experiments. The results verify that UK-PST has a higher effective secret transmission rate than that of IK-PST for scenarios with both pairwise and group users.

Physical-layer based secret key generation (SKG) becomes a research focus as it solves key distribution problem which is difficult in traditional cryptographic mechanism. To remove the disagreements caused by imperfect reciprocity of communicating parties, information reconciliation is a critical process in SKG to obtain symmetric keys. Various reconciliation schemes are proposed, e.g. BBBSS, Cascade, BCH code and Turbo code. Reconciliation efficiency is a common evaluation index which takes reconciliation success rate and information leakage rate into account. However, time delay caused by information interaction and computation overhead may affect reconciliation performance under specific scenarios. Therefore, a comprehensive evaluation metric is required to compare existing schemes. Besides, channel condition changes all the time in real mobile communication systems, and most existing reconciliation schemes only work well in certain channel conditions. Hence, a reconciliation scheme which can adapt to time-varying channel condition is required. In this paper, we introduce a novel comprehensive reconciliation efficiency index (CREI) to evaluate existing reconciliation schemes and propose an adaptive information reconciliation scheme selection (AIRSS) protocol to maximize CREI. The simulation results show the superiority of AIRSS and present recommendations of reconciliation scheme selection in different scenarios.

The user reviews of mobile apps are important assets that reflect the users' needs and complaints about particular apps regarding features, usability, and designs. From investigating the content of such reviews, the app developers can acquire useful information guiding the future maintenance and evolution work. Previous studies on opinion mining in mobile app reviews have provided various approaches to eliciting such critical information. A particular update of an app can provide changes to the app that result in users' reversed opinions, as well as, specific new complaints or praises. However, limited studies focus on eliciting the user opinions regarding a particular mobile app update, or the impact the update imposes. In this paper, we propose a method for systematically studying and analyzing the evolution of the users' opinions taking into consideration a set of mobile app updates. For doing so, we compare the topics appearing in the users' reviews before and after the updates. We also validate the method with an experiment on an existing mobile app.

The Mobility Requirements Engineering Tool (MoRE) is designed to facilitate the requirement analysis process of mobile app development towards the enhancement of mobile app mobility. The tool contains features of scenario creation and management, contexts and ways of interaction analysis and specification, as well as requirements change management.

Good software development and particularly maintenance practices form an important factor for success in software business. If one wants to constantly produce new successful releases of the applications, a proper efficient software maintenance process is the key. In this work, we study data from mobile application maintenance to understand and conceptualize how mobile application maintenance takes place. Based on the data on release history, we deduce different mobile application maintenance models from the perspectives of maintenance scheduling and maintenance requirements.

Rights exporting plays an essential role in the battle of fighting for Digital Rights Management (DRM) interoperability. The decision making process determines the results of rights exporting. In order to achieve optimal results in rights exporting, we leverage the process with algorithms for rights adaptation and rights decomposition. We also demonstrate how the proposed process can lead to improved results.

The incompatibility of various Digital Rights Management (DRM) systems remain as an obstacle hampering user experience and business on DRM based services. To increase DRM interoperability, rights exporting currently seems a preferred solution. Based on an earlier DRM model [8,9], we extend and consolidate the concept of rights adaptation in rights exporting. We analyse different ways of adapting rights to be exported and present a general rights adaptation framework.