Transforming informal stakeholder descriptions into clear and actionable software requirements is a critical challenge in requirements engineering. Existing Artificial Intelligence (AI)- based tools can process natural language but often overlook alignment with underlying business processes and coverage of all relevant scenarios. This paper proposes a hybrid neuralsymbolic framework, referred to as Process-Aware Requirement Generation (PARG), which integrates transformer-based process recognition with ontology-guided requirement generation. PARG extracts key process elements, such as actors, actions, conditions, and outcomes from user stories, maps them to domain-specific processes, and instantiates structured requirement statements using predefined templates. The framework further validates consistency and evaluates coverage to ensure completeness and traceability. By combining language understanding with structured process knowledge, PARG reduces manual effort, supports improved traceability, and produces requirements that are coherent, process-aware, and aligned with real-world workflows.

—Digital Twin (DT) ecosystems—including low-power IoT networks, cyber-physical systems, and virtual replicas of industrial assets—are highly vulnerable to zero-day threats that exploit the semantic gap between physical states and virtual expectations. These environments face challenges such as heterogeneous device topologies, evolving data distributions (concept drift), and limited computational resources, all of which undermine traditional Intrusion Detection Systems (IDSs). Existing methods often produce high false positives due to opaque statistical models that fail to distinguish benign traffic bursts from genuine attacks, or lack the adaptability to update their threat models in real-time. To address this, we introduce Ψ-Risk-DT, a neurosymbolic framework that integrates entropy-based anomaly detection with an Associated Random Neural Network (ARNN) and a semantic reasoning layer based on RDF/SPARQL. A key neurosymbolic operator, Ψ, couples neural pattern recognition with dynamic se mantic updates, triggering adaptive analysis when entropy spikes indicate potential zero-day behaviour. Additionally, a Modular Semantic Update (MSU) mechanism rewrites only the relevant portions of the knowledge graph, minimizing computational overhead in resource-constrained environments. The architecture is optimized via a hybrid loss function balancing detection accuracy, graph consistency, and semantic alignment. Evaluated on out-of-distribution variants of established IoT/DT benchmarks (Kitsune, WiseML 2024, Sec4ML 2023), Ψ-Risk-DT detects zero-day threat patterns without relying on known signatures, achieving 85–95% detection rates for unseen attacks. It reduces false positives by 20–40% compared to state of-the-art baselines, delivers sub-second latency (≈ 247ms, a 30% improvement over neural-only IDSs), and cuts symbolic processing load by up to 88% through MSU. Overall, Ψ-Risk-DT provides resilient and explainable protec tion for DT ecosystems, enabling real-time identification of zero day threats with low overhead and traceable reasoning pathways. This advances neurosymbolic cybersecurity for IoT and paves the way for adaptive defenses in critical infrastructures.

Domain-Specific Languages, apart from the design and formal definition aspects involved to build, also require Model-to-Text (M2T) transformations to generate executable code. Authoring the M2T templates is a manual, labor-intensive process that often generates frustrating, time consuming errors. And, although Large Language Models have advanced code and grammar generation, the automated synthesis of downstream Model-to-Text templates still remains largely unaddressed. In the context of software engineering and model-driven development, automating such transformations addresses a core challenge in modern software toolchain construction. This paper presents a work-in-progress multi-agent system that automatically generates production-ready Jinja2 templates from a textX grammar, natural language requirements and sample model instances. The architecture decomposes the generation task into seven stages orchestrated by eleven specialized agents, employing deterministic runtime introspection to provide ground-truth structural data. To ensure reliability, the generation process is coupled with a rigorous three-level deterministic validation loop that evaluates template syntax, rendering execution and target-language correctness without relying on self-assessment by the language models. We demonstrate the pipeline on two structurally versatile domains, specifically a recursive calculator and a declarative smart home automation language, illustrating its ability to produce functional templates, rendered code and test artifacts across diverse grammar paradigms.

The evolution of software engineering is increasingly driven by the integration of artificial intelligence and digital paradigms. In critical domains such as medical and biological imaging, modern software systems are transitioning from static, rule-based workflows to dynamic, AI-powered environments. This paper presents the design, implementation, and preliminary validation of an advanced, fully automated software pipeline for Transmission Electron Microscopy image analysis to address software engineering and analytical challenges in tendon fibril segmentation. The proposed architecture replaces a previous hybrid segmentation approach with a deep learning model based on the ViT-UNet architecture, integrating targeted preprocessing modules, advanced segmentation capable of capturing both local details and global spatial relationships, and an automated feature extraction and clustering engine. Initial experimental results show an improvement in clustering accuracy from 57.14% to 64.71%. While these findings suggest the potential of Transformer-based architectures to enhance medical image analysis, they also highlight the need for further evaluation on larger datasets to establish broader statistical significance and validate their overall effectiveness.