Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering

TL;DR

This paper examines the rise of agentic AI systems in software engineering, proposing a new architecture, contrasting with traditional SDLC, and analyzing empirical evidence of performance, productivity, and labor impact.

Contribution

It introduces a six-layer reference architecture for agentic systems, compares agentic SDLC with traditional SDLC, and consolidates empirical data on performance and societal effects.

Findings

Performance improved from 1.96% to 78.4% on SWE-bench Verified

Time savings of 13.6%-55.8% in controlled studies

49% of jobs sampled used AI for at least a quarter of tasks

Abstract

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.