Page 2 of 369
Abstract: Background/Objectives: Large language models (LLMs) are increasingly explored for clinical decision support and digital health applications. However, reliable diagnostic assistance remains challenging for low-resource medical languages such as Turkish due to limited source grounding, transparency, clinical safety, and localized medical knowledge. This study presents TurkishMedLLM, a source-grounde...
Abstract: The emergence of AI agents is expected to reshape software engineering by moving beyond AI as assistants towards systems capable of planning, executing, and evaluating development tasks with increasing autonomy. This transition is particularly significant for embedded software organizations, where strict requirements for quality, traceability, verification, and long-term maintainability often appl...
Abstract: This study examines tool-augmented Large Language Model (LLM) systems for supporting Root Cause Analysis (RCA) of nightly test failures at Westermo Network Technologies AB. Nightly test executions produce heterogeneous test data and logs that practitioners currently inspect manually across multiple sources. We implemented an RCA workflow in single-agent and orchestrated multi-agent configurations,...
Abstract: Over the last decade, behavior trees (BT) have become one of the dominant behavior models for coordinating missions of robotic systems. Yet empirical evidence on BT adoption in real-world contexts remains limited, especially regarding practitioners experiences and practices. Without practitioner-grounded evidence from both academic and industrial settings, the research community risks developing g...
Abstract: Tiny twins are compact behavioral models derived from timed actor models for selected observable messages. When a source model evolves, regenerating its tiny twin requires state-space exploration and reduction even if the relevant behavior is unchanged. We present a static analysis for Timed Rebeca that compares backward slices of Rebeca dependence graphs for a given set of observable message name...
Abstract: Prompt engineering is increasingly used across Software Engineering (SE) activities, including requirements analysis, coding, testing, documentation, repository analysis, and planning. Yet prompts and related instruction artifacts are often created and evolved through task-specific and informal practices, with limited support for their systematic evaluation, management, traceability, and governanc...
Abstract: Large language models have shown promising capabilities in code refactoring, but existing approaches remain limited to method-level tasks. In this paper, we envision LLM-based refactoring as a continuous component of software maintenance rather than a tool invoked only for occasional manual refactoring. Under this vision, AI agents continuously monitor, evaluate, and improve codebases against expl...
Abstract: Future 6G IoT smart environments will comprise large populations of mobile cyber-physical entities operating under stringent reliability and latency requirements. Unlike traditional static IoT deployments, mobility becomes an intrinsic system property that continuously alters network topology, communication quality, and resource availability. Consequently, maintaining reliable and deterministic co...
Abstract: Exploring large SysML v2 models is challenging due to their size and complexity, as answering analysis questions often requires manual navigation across many interconnected elements. Therefore, this paper proposes an approach for automatically generating custom views that support model exploration based on the analysis needs of system engineers. The approach enables the definition of view configur...
Abstract: Traffic orchestration is increasingly discussed as a means to coordinate connected, automated, and conventional mobility systems across urban and highway networks. However, transport systems are open systems of systems: vehicles, fleet operators, mobility services, infrastructure managers, public authorities, and individual road users remain operationally and managerially independent. In routine o...
Abstract: Orchestration of collaborating Systems of Systems (SoS) is highly challenging because its constituent systems (CSs) are autonomous, heterogeneous, and distributed. These challenges vary from resource allocation, SoS-level decisionmaking to achieve optimal performance, deterministic behaviour and above all ensuring safety of operations. These challenges also increase drastically when we need to con...
Abstract: Real-time communication demands the ability to deterministically schedule time-sensitive flows and is usually performed using worst-case delays. The resource allocation protocol (RAP) for Time Sensitive Networks (TSN) as defined in the IEEE P802.1DD provides a simplified approach to allocate streams using maximum per-hop delay along the path from the source of a stream to its destination, thereby ...
Abstract: Cyber-physical systems (CPSs) in critical domains such as self-driven cars and unmanned aerial vehicles involve complex interactions between safety and security concerns. Failures in CPSs such as self-driven cars are caused either by hardware/software component faults or attacks. The identification of hazards, their risks, and root causes is addressed by Safety Engineering, e.g., using Fault Tree ...
Page 2 of 369