Abstract

Abstract
This paper explores the potential of Large Language Models (LLM) to optimize various stages of the software development lifecycle, including requirements elicitation, architecture design, diagram creation, and implementation. The study is grounded in a real-world case, where development time and result quality are compared with and without LLM assistance. This research underscores the possibility of applying prompt patterns in LLM to support and enhance software development activities, focusing on a B2C digital commerce platform centered on fashion retail, designated LUNA. The methodology adopted is Design Science, which follows a practical and iterative approach. Requirements, design suggestions, and code samples are analyzed before and after the application of language models. The results indicate substantial advantages in the development process, such as improved task efficiency, faster identification of requirement gaps, and enhanced code readability. Nevertheless, challenges were observed in interpreting complex business logic. Future work should explore the integration of LLM with domain-specific ontologies and business rule engines to improve contextual accuracy in code and model generation. Additionally, refining prompt engineering strategies and combining LLM with interactive development environments could further enhance code quality, traceability, and explainability.

Abstract
Vehicle cybersecurity has emerged as a critical concern, driven by innovation in the automotive industry, e.g., autonomous, electric, or connected vehicles. Current efforts to address these challenges are constrained by the limited computational resources of vehicles and the reliance on connected infrastructures. This motivated the foundation of Vehicle Security Operations Centers (VSOCs) that extend IT-based Security Operations Centers (SOCs) to cover the entire automotive ecosystem, both the in-vehicle and off-vehicle scopes. Security Orchestration, Automation, and Response (SOAR) tools are considered key for implementing an effective cybersecurity solution. However, existing state-of-the-art solutions depend on infrastructure networks such as 4G, 5G, and WiFi, which often face scalability and congestion issues. To address these limitations, we propose a novel SOAR architecture EVSOAR that leverages the EV charging stations for connectivity and computing to enhance vehicle cybersecurity. Our EV-specific SOAR architecture enables real-time analysis and automated responses to cybersecurity threats closer to the EV, reducing cellular latency, bandwidth, and interference limitations. Our experimental results demonstrate a significant improvement in latency, stability, and scalability through the infrastructure and the capacity to deploy computationally intensive applications that are otherwise infeasible within the resource constraints of individual vehicles.

Abstract
In a survey of Belgian logistics service providers, the efficiency of first-mile pickup operations was identified as a key area for improvement, given the increasing number of returns in e-commerce, which has a significant impact on traffic congestion, carbon emissions, energy consumption and operational costs. However, the complexity of first-mile pickup operations, resulting from the small number of parcels to be collected at each pickup location, customer time windows, and the need to efficiently accommodate the highly heterogeneous cargo inside the vans, has hindered the development of real-world solution approaches. This article tackles this operational problem as a vehicle routing problem with time windows, time-dependent travel durations, and split pickups and integrates practical 3D container loading constraints such as vertical and horizontal stability as well as amore realistic reachability constraint to replace the classical Last In First Out (LIFO) constraint. To solve it, we propose a three-phase heuristic based on a savings constructive heuristic, an extreme point concept for the loading aspect and a General Variable Neighborhood Search as an improvement phase for both routing and packing. Numerical experiments are conducted to assess the performance of the algorithm on benchmark instances and new instances are tested to validate the positive managerial impacts oncost when allowing split pickups and on driver working duration when extending customer time windows. In addition, we show the impacts of considering the reachability constraint oncost and of the variation of speed during peak hours on schedule feasibility.

Abstract
This document presents the outcomes of the Dagstuhl Seminar Roadmap for Responsible Robotics, held in September 2023 at the Leibniz Center for Informatics, Schloss Dagstuhl, Germany. The seminar brought together researchers from the fields of robotics, computer science, social and cognitive sciences, and philosophy with the aim of charting a path toward improving responsibility in robotic systems. Through intensive interdisciplinary discussions centered on the various values at stake as robotics increasingly integrates into human life, the participants identified key priorities to guide future research and regulatory efforts. The resulting road map outlines actionable steps to ensure that robotic systems coevolve with human societies, promoting human agency and humane values rather than undermining them. Designed for diverse stakeholders-researchers, policy makers, industry leaders, practitioners, nongovernmental organizations (NGOs), and civil society groups-this road map provides a foundation for collaborative efforts toward responsible robotics.

Abstract
Online retail is transforming the way distribution networks are managed. One prominent change is that retailers can now use their full network to fulfil orders. This process involves allocating orders to fulfilment nodes and, depending on the setting, can include other operational decisions, such as order consolidation, shipping mode selection and product substitution. This order allocation problem (OAOR) has garnered considerable attention in recent years. However, there is no comprehensive view of what has been done in the literature, nor a consistent terminology across papers, which makes it hard to position existing work and identify research gaps. To address these concerns, we conduct a systematic literature review, where we find over 60 articles contributing to the OAOR literature. From this review, we formulate the baseline problem, consider multiple extensions, and identify key problem characteristics. Additionally, we analyse and categorize the solution methods found based on the optimization mechanism, policy class, and incorporation of future information and learning. Our review points to several avenues for future research, both in problems and in solution methods. © 2025 The Authors