A Research Roadmap for Augmenting Software Engineering Processes and Software Products with Generative AI

2025-10-30

AI Summary

Generative AI (GenAI) is transforming software engineering (SE), yet a systematic, theory-grounded research agenda for GenAI-enhanced SE remains absent. Method: Adopting design science research, this study integrates a rapid literature review, collaborative workshops at the International Conference on Software Engineering (ICSE/FSE), and three rounds of iterative validation. Drawing on McLuhan’s Laws of Media, it distills four foundational GenAI-SE paradigms and identifies critical challenges and opportunities. Contribution/Results: The work delivers a transparent, reproducible roadmap culminating in ten forward-looking predictions for SE through 2030. Validated independently by external research teams, this is the first comprehensive framework bridging theoretical rigor and practical feasibility for GenAI-driven SE innovation—guiding methodological advancement, tool development, and future research directions.

Technology Category

• Search and Optimization: Metareasoning and Metaheuristics
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Generative AI (GenAI) is rapidly transforming software engineering (SE) practices, influencing how SE processes are executed, as well as how software systems are developed, operated, and evolved. This paper applies design science research to build a roadmap for GenAI-augmented SE. The process consists of three cycles that incrementally integrate multiple sources of evidence, including collaborative discussions from the FSE 2025 "Software Engineering 2030" workshop, rapid literature reviews, and external feedback sessions involving peers. McLuhan's tetrads were used as a conceptual instrument to systematically capture the transforming effects of GenAI on SE processes and software products.The resulting roadmap identifies four fundamental forms of GenAI augmentation in SE and systematically characterizes their related research challenges and opportunities. These insights are then consolidated into a set of future research directions. By grounding the roadmap in a rigorous multi-cycle process and cross-validating it among independent author teams and peers, the study provides a transparent and reproducible foundation for analyzing how GenAI affects SE processes, methods and tools, and for framing future research within this rapidly evolving area. Based on these findings, the article finally makes ten predictions for SE in the year 2030.

Problem

• Building roadmap for GenAI-augmented software engineering processes
• Identifying research challenges in GenAI-enhanced software development
• Analyzing GenAI effects on software engineering methods and tools

Innovation

• Design science research builds GenAI roadmap
• McLuhan's tetrads capture GenAI transformation effects
• Multi-cycle process cross-validates research directions