🤖 AI Summary
Traditional software engineering struggles to address the development of autonomous, probabilistic systems powered by large language models. This work proposes a new paradigm—AI-native software engineering—that shifts the focus from writing deterministic code to supervising agent workflows, redefining the engineer’s role as an “agent engineer” whose primary output is an intelligent agent system. The paradigm encompasses key techniques including reasoning-action loops, context engineering, tool invocation, memory mechanisms, and behavioral drift control. It emphasizes statistical evaluation to ensure reliable system behavior under uncertainty and establishes an outcome-oriented accountability framework. Drawing on empirical studies since 2022, the paper demonstrates that disciplined human-agent collaboration outperforms full automation and introduces a governance framework to mitigate emerging risks such as indirect prompt injection.
📝 Abstract
Software engineering is experiencing its most significant transformation since the emergence of high-level programming languages. As large language models (LLMs) increasingly enable sustained, multi-step, tool-mediated execution, engineering value is shifting from writing deterministic code to supervising probabilistic and autonomous behavior. This paper argues that AI-Native Software Engineering is a paradigm shift rather than a mere tooling advance, creating a new professional archetype: the Agentic Engineer, whose primary artifact is the agentic system rather than the program.
We characterize this transition through three changes: (i) the unit of work shifts from functions to supervised agent workflows, (ii) correctness shifts from binary assertions to statistical evaluation under uncertainty, and (iii) accountability shifts from code authorship to outcome ownership. Drawing on post-2022 research, we compare traditional and agentic engineering roles and define core mechanisms of autonomous agents, including reasoning-acting loops, context engineering, tool use, memory, behavioral drift, and compositional error.
We place human-AI collaboration within socio-technical frameworks and examine mixed empirical evidence. While some studies report productivity gains, others show slowdowns among experienced developers, highlighting disciplined oversight rather than automation as the critical competency. Using established governance frameworks, we identify required skills and risks, including indirect prompt injection. We conclude that the future is one of symbiosis rather than substitution: agentic engineering builds upon and depends on classical software engineering principles.