Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering
For software engineering researchers and practitioners, this paper provides a structured overview and empirical consolidation of the shift to agentic AI, though it is largely a synthesis of existing work rather than new results.
This paper characterizes the transition from code-completion tools to agentic AI systems in software engineering, proposing a six-layer reference architecture and an Agentic SDLC. It consolidates empirical evidence showing a rise from 1.96% to 78.4% on SWE-bench Verified and 13.6%-55.8% time savings, and identifies five open problems for the field.
The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated at the granularity of a line or function, modern agentic systems -- Claude Code, OpenAI Codex CLI, Google Jules, Devin, OpenHands, SWE-agent, MetaGPT, ChatDev, and DeepMind's AlphaEvolve -- operate at the granularity of a repository, a feature, or an algorithm. We synthesize work from Anthropic, OpenAI, Google DeepMind, Microsoft Research, Princeton, Stanford, and the broader academic community to characterize this transition. We propose a six-layer reference architecture for agentic software engineering systems, contrast a traditional Software Development Lifecycle (SDLC) with an emerging Agentic SDLC (A-SDLC), and consolidate empirical evidence on performance (a rise from 1.96% to 78.4% on SWE-bench Verified between October 2023 and April 2026), productivity (13.6%-55.8% time savings across controlled studies), and labor-market impact (49% of jobs sampled by Anthropic in 2026 saw AI used for at least a quarter of their tasks). We argue that the central object of inquiry has shifted from code generation to delegated execution under human supervision, and we identify five open problems -- evaluation, governance, technical debt, skill redistribution, and the economics of attention -- that will determine whether the agentic transition is net-positive for the discipline.