generative ai integration

This study addresses the lack of a systematic understanding of generative artificial intelligence’s role across the full software development lifecycle. Through a systematic literature review complemented by structured surveys of 65 developers, this work integrates empirical data with existing research to comprehensively evaluate the real-world impact and adoption patterns of large language models (LLMs) in each development phase. Findings indicate that over 70% of developers save more than 50% of their time on boilerplate code generation and documentation tasks, and 79% use browser-based LLMs daily. While nascent governance mechanisms are emerging, benefits in early-stage activities—such as requirements elicitation and architectural design—remain limited. The results suggest that generative AI is shifting the locus of development value from coding toward upstream design activities.

Low modeling efficiency in the MBSE system design phase and heavy manual effort required for simulation code generation hinder scalable, reliable complex-system development. Method: This paper proposes a generative-AI–driven systems modeling methodology: it introduces an extensible simulation model template framework integrating fine-tuned large language models (LLMs), SysML/Modelica modeling languages, a reusable simulation model library, and generative data augmentation techniques—enabling end-to-end intelligent generation of executable simulation models (including physics-based property modeling) directly from design documentation. Contribution/Results: We establish the first MBSE-specific generative methodology and a dedicated evaluation metric suite. Experiments on mainstream open-source Transformer models demonstrate significant improvements in generated model accuracy, cross-model consistency, and engineering reusability. The approach provides a verifiable, GenAI-powered technical pathway for modeling complex cyber-physical systems within MBSE workflows.

This study investigates the transformative impact of generative artificial intelligence (GenAI) on human-computer interaction paradigms within integrated development environments (IDEs), along with its associated challenges and opportunities. Through a four-day interdisciplinary workshop at the Shonan Meeting 222, involving 33 experts from software engineering, artificial intelligence, and human-computer interaction, the research systematically identifies four core themes shaping the future evolution of IDEs under GenAI influence. The findings highlight GenAI’s potential to enhance developer productivity in tasks such as code generation, testing, review, and repair, while articulating key research challenges and practical opportunities. This work provides a foundational roadmap for advancing collaborative programming research in human-AI co-development contexts.

The integration of generative AI (GenAI) into the software development lifecycle (SDLC) faces critical uncertainties regarding reliability, accountability, security, and data privacy. Method: This study—conducted collaboratively by over 30 European industry, academic, and research institutions—establishes a comprehensive GenAI adoption vision and a co-innovation framework spanning requirements, design, coding, testing, and operations. It introduces a five-year technology roadmap and develops a verifiable toolchain integrating code generation, quality assurance, security analysis, and trustworthy AI. Contribution/Results: The project delivers cross-sector consensus-based practice guidelines and functional prototypes, enabling the reliable, scalable deployment of AI-driven software engineering. It further supports the transformation and reskilling of software engineers to meet evolving role demands in GenAI-augmented development environments.

This study addresses key challenges in engineering problem-solving—ambiguous requirements, difficulty in cross-domain mapping, weak multimodal data integration, and inefficient exploration of solution spaces—by proposing “Generative Optimization,” a novel paradigm. Methodologically, it synergistically integrates generative AI (e.g., large language models, diffusion models, multimodal generators) with classical optimization techniques (e.g., gradient-based and evolutionary algorithms): GenAI drives requirement inference, cross-domain semantic bridging, multimodal input understanding, and large-scale solution generation, while optimization modules ensure constraint satisfaction and solution precision. We establish, for the first time, a systematic conceptual framework, elucidate complementary mechanisms between generative and optimization components, and propose hybrid algorithm design principles and critical research directions. Empirical validation across multiple engineering domains demonstrates the paradigm’s scalability, interpretability, and robustness, offering a principled pathway toward AI-augmented engineering decision-making.

This study addresses the fragmented empirical evidence on generative AI’s (GenAI) impact on enterprise architecture (EA) work within agile software organizations. To synthesize current knowledge rigorously, we conducted a systematic literature review (SLR) adhering to Kitchenham and PRISMA guidelines, screening 1,697 publications to identify 33 empirical studies. Our analysis reveals, for the first time, three core GenAI roles in EA—ideation support for architectural design, rapid generation of architecture artifacts, and data-informed decision support—as well as four critical risks: technical debt accumulation, governance failure, role ambiguity, and model hallucination. We further identify emerging capability requirements, including prompt engineering and model evaluation. Based on these findings, we propose a research agenda centered on capability development, adaptive governance frameworks, and human-AI collaboration mechanisms. This work establishes a theoretical foundation and actionable pathways for responsible, sustainable integration of GenAI into EA practice.

Despite growing interest in integrating generative AI (GenAI) into self-adaptive systems (SASs), its advantages and challenges remain poorly understood. To address this gap, this study conducts the first cross-domain systematic literature review spanning software engineering, human-computer interaction, autonomous systems, and AI—augmented by large language model–assisted data analysis and logical reasoning—to assess GenAI’s technical fit within each component of the MAPE-K feedback loop. We propose a novel dual-dimensional framework—“autonomy enhancement” and “human-AI collaboration”—to systematically characterize GenAI’s core strengths (e.g., dynamic modeling, intent understanding, policy generation) and critical limitations (e.g., explainability, real-time responsiveness, trustworthiness assurance). Finally, we derive a forward-looking research roadmap covering technical challenges, validation methodologies, and practical implementation pathways—providing a cohesive foundation for both theoretical advancement and industrial deployment of GenAI-powered SASs.

This study addresses the widespread lack of understanding of generative AI among energy sector employees, which hinders the identification of viable application entry points and implementation pathways. Through semi-structured interviews, internal document analysis, and on-site observations, the research systematically identifies five high-potential application scenarios: report generation, forecasting, data processing, equipment maintenance, and anomaly detection. It proposes a gradual deployment approach for generative AI that aligns with existing workflows. This work establishes the first practical framework for implementing generative AI in the energy industry, offering reusable design strategies for LLM-based agent workflows and providing both theoretical grounding and actionable guidance for AI-driven transformation in heavy industrial sectors.

This study investigates whether compact generative AI (GenAI) language models can match large language models (LLMs) in application behavior understanding—particularly malware detection. We systematically evaluate GenAI models of varying scales on code understanding, behavioral analysis, and classification tasks, using accuracy, precision, recall, and F1-score as metrics. Results show that while compact GenAI models achieve marginally lower overall accuracy than LLMs, they attain competitive performance on critical metrics—especially recall and F1-score—and exhibit substantially faster inference, lower memory footprint, and reduced deployment cost. The primary contribution is empirical evidence that compact GenAI models deliver high discriminative capability and computational efficiency under resource constraints, offering a lightweight, reliable, and deployable alternative for application behavior analysis. Rather than replacing LLMs, these models serve as complementary tools, extending practical applicability to edge and latency-sensitive environments.

This study addresses the fragmentation of developer experience and low-level human-AI collaboration in modern IDEs by investigating how generative AI (GenAI) reshapes the IDE paradigm. Through a systematic, interdisciplinary analysis—integrating software engineering, AI, and human-computer interaction—we examine GenAI’s integration pathways into core IDE tasks: code generation, testing, review, and repair. We identify its dual role in elevating programming abstraction and redefining interactive modalities. Our key contribution is a novel “AI-Native IDE” evolutionary framework, which pinpoints four critical research directions: explainability, human-centered adaptation, standardized evaluation benchmarks, and shared responsibility in AI-assisted development. Findings were synthesized in the Shonan Meeting 222 consensus report, establishing a cross-disciplinary theoretical foundation and actionable roadmap for next-generation, GenAI-driven development environments.