Ahmad Hatahet

Ahmad Hatahet, Christoph Knieke, Andreas Rausch

Software Architecture Descriptions (SADs) are essential for managing the inherent complexity of modern software systems. They enable high-level architectural reasoning, guide design decisions, and facilitate effective communication among diverse stakeholders. However, in practice, SADs are often missing, outdated, or poorly aligned with the system's actual implementation. Consequently, developers are compelled to derive architectural insights directly from source code-a time-intensive process that increases cognitive load, slows new developer onboarding, and contributes to the gradual degradation of clarity over the system's lifetime. To address these issues, we propose a semi-automated generation of SADs from source code by integrating reverse engineering (RE) techniques with a Large Language Model (LLM). Our approach recovers both static and behavioral architectural views by extracting a comprehensive component diagram, filtering architecturally significant elements (core components) via prompt engineering, and generating state machine diagrams to model component behavior based on underlying code logic with few-shots prompting. This resulting views representation offer a scalable and maintainable alternative to traditional manual architectural documentation. This methodology, demonstrated using C++ examples, highlights the potent capability of LLMs to: 1) abstract the component diagram, thereby reducing the reliance on human expert involvement, and 2) accurately represent complex software behaviors, especially when enriched with domain-specific knowledge through few-shot prompting. These findings suggest a viable path toward significantly reducing manual effort while enhancing system understanding and long-term maintainability.

Mohammad Abboush, Ahmad Hatahet, Andreas Rausch

A well-known testing method for the safety evaluation and real-time validation of automotive software systems (ASSs) is Fault Injection (FI). In accordance with the ISO 26262 standard, the faults are introduced artificially for the purpose of analyzing the safety properties and verifying the safety mechanisms during the development phase. However, the current FI method and tools have a significant limitation in that they require manual identification of FI attributes, including fault type, location and time. The more complex the system, the more expensive, time-consuming and labour-intensive the process. To address the aforementioned challenge, a novel Large Language Models (LLMs)-assisted fault test cases (TCs) generation approach for utilization during real-time FI tests is proposed in this paper. To this end, considering the representativeness and coverage criteria, the applicability of various LLMs to create fault TCs from the functional safety requirements (FSRs) has been investigated. Through the validation results of LLMs, the superiority of the proposed approach utilizing gpt-4o in comparison to other state-of-the-art models has been demonstrated. Specifically, the proposed approach exhibits high performance in terms of FSRs classification and fault TCs generation with F1-score of 88% and 97.5%, respectively. To illustrate the proposed approach, the generated fault TCs were executed in real time on a hardware-in-the-loop system, where a high-fidelity automotive system model served as a case study. This novel approach offers a means of optimizing the real-time testing process, thereby reducing costs while simultaneously enhancing the safety properties of complex safety-critical ASSs.

Moustapha El Outmani, Manthan Venkataramana Shenoy, Ahmad Hatahet et al.

Agile organizations increasingly rely on automated regression testing to sustain rapid, high-quality software delivery. However, as systems grow and requirements evolve, a persistent bottleneck arises: test specifications are produced faster than they can be transformed into executable scripts, leading to mounting manual effort and delayed releases. In partnership with Hacon (a Siemens company), we present an agentic AI approach that generates system-level test scripts directly from validated specifications, aiming to accelerate automation without sacrificing human oversight. Our solution features a retrieval-augmented, multi-agent architecture integrated into Hacon's agile workflows. We evaluate this system through a mixed-method analysis of industrial artifacts and practitioner feedback. Results show that the AI teammate significantly increases test script throughput and reduces manual authoring effort, while underscoring the ongoing need for clear specifications and human review to ensure quality and maintainability. We conclude with practical lessons for scaling regression automation and fostering effective Human-AI collaboration in agile environments.