Toward Agentic Software Engineering Beyond Code: Framing Vision, Values, and Vocabulary

2025-10-22

AI Summary

Current Agentic AI applications in software engineering (SE) remain narrowly focused on code generation, neglecting broader lifecycle activities—including requirements analysis, design, testing, operations, and collaboration—and overlooking socio-technical dimensions. Method: Grounded in SE evolution principles and emerging agent frameworks, this work integrates empirical field studies with conceptual modeling to systematically extend agent capabilities across the full SE lifecycle. Contribution/Results: We introduce “Agentic Software Engineering” (Agentic SE) as a novel paradigm, establishing its first comprehensive theoretical foundation—comprising a vision statement, core values, a principle-based architecture, and a standardized terminology. Concurrently, we release a vocabulary design guideline to foster community alignment. The resulting framework is scalable, controllable, and predictable, enabling rigorous academic research, reproducible experimentation, and sustainable industrial adoption. This work bridges foundational AI agent research with SE practice, advancing both disciplines through a socio-technically aware, lifecycle-integrated perspective.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Application Domains: Software Engineering

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Agentic AI is poised to usher in a seismic paradigm shift in Software Engineering (SE). As technologists rush head-along to make agentic AI a reality, SE researchers are driven to establish agentic SE as a research area. While early visions of agentic SE are primarily focused on code-related activities, early empirical evidence calls for a consideration of a range of socio-technical concerns to make it work in practice. This paper contributes to the emerging community vision by: (a) recommending an expansion of its scope beyond code, toward a 'whole of process' vision, grounding it in SE foundations and evolution and emerging agentic SE frameworks, (b) proposing a preliminary set of values and principles to guide efforts, and (c) sharing guidance on designing/using well-defined vocabulary for agentic SE. It is hoped that these ideas will encourage community collaborations and steer the SE community towards laying strong foundations of agentic SE so its not only inevitable but also deliberate and desirable in the long run.

Problem

• Expanding agentic SE scope beyond code to whole process vision
• Establishing values and principles for agentic AI in software engineering
• Developing well-defined vocabulary for agentic software engineering foundations

Innovation

• Expanding agentic SE scope beyond code activities
• Proposing values and principles to guide agentic SE
• Designing well-defined vocabulary for agentic SE