Towards AI-Native Software Engineering (SE 3.0): A Vision and a Challenge Roadmap
Ahmed E. Hassan, Gustavo A. Oliva, Dayi Lin, Boyuan Chen, Zhen Ming, Jiang
TL;DR
SE2.0 delivers AI-assisted software engineering but suffers from cognitive overload, inefficient training on vast uncurated data, and biased, bloated code. The authors propose SE3.0, an AI-native, intent-centric paradigm where AI teammates engage in back-and-forth conversations with humans to convert intents into runnable software, supported by a stack of Teammate.next, IDE.next, Compiler.next, Runtime.next, and FM.next. They advocate curriculum-driven FMware (FM.next) and data-flywheel feedback to achieve knowledge-driven efficiency, along with multi-objective optimization in synthesis and SLA-aware runtimes for practical deployment. The paper also maps a roadmap of challenges—alignment speed, synthesis efficiency, runtime performance, FM understanding, and prompt-engineering elimination—alongside broader questions about education, languages, UI, benchmarks, and open innovation. Together, these ideas aim to democratize AI-native software engineering and redefine how humans and AI co-create high-quality software at scale.
Abstract
The rise of AI-assisted software engineering (SE 2.0), powered by Foundation Models (FMs) and FM-powered coding assistants, has shown promise in improving developer productivity. However, it has also exposed inherent limitations, such as cognitive overload on developers and inefficiencies. We propose a shift towards Software Engineering 3.0 (SE 3.0), an AI-native approach characterized by intent-centric, conversation-oriented development between human developers and AI teammates. SE 3.0 envisions AI systems evolving beyond task-driven copilots into intelligent collaborators, capable of deeply understanding and reasoning about software engineering principles and intents. We outline the key components of the SE 3.0 technology stack, which includes Teammate.next for adaptive and personalized AI partnership, IDE.next for intent-centric conversation-oriented development, Compiler.next for multi-objective code synthesis, and Runtime.next for SLA-aware execution with edge-computing support. Our vision addresses the inefficiencies and cognitive strain of SE 2.0 by fostering a symbiotic relationship between human developers and AI, maximizing their complementary strengths. We also present a roadmap of challenges that must be overcome to realize our vision of SE 3.0. This paper lays the foundation for future discussions on the role of AI in the next era of software engineering.