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

• URL: http://arxiv.org/abs/2604.26275v1
• Date: Wed, 29 Apr 2026 04:06:47 GMT
• Title: Agentic AI in the Software Development Lifecycle: Architecture, Empirical Evidence, and the Reshaping of Software Engineering
• Abstract summary: Modern agentic systems operate at the granularity of a repository, a feature, or an algorithm.<n>We propose a six-layer reference architecture for agentic software engineering systems.<n>We argue that the central object of inquiry has shifted from code generation to delegated execution under human supervision.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Code as Agent Harness [107.31925305395957]
  In emerging agentic systems, code is no longer only a target output.<n>Code increasingly serves as an operational substrate for agent reasoning, acting, environment modeling, and execution-based verification.<n>This survey provides a unified roadmap toward executable, verifiable, and stateful AI agent systems.
  arXiv  Detail & Related papers  (2026-05-18T17:59:03Z)
• AcademiClaw: When Students Set Challenges for AI Agents [69.70303995121154]
  AcademiClaw is a benchmark of 80 complex, long-horizon tasks sourced directly from university students' real academic disconnects.<n>We show that even the best of models achieves only a 55% pass rate.<n>We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community.
  arXiv  Detail & Related papers  (2026-05-04T14:40:42Z)
• Workstream: A Local-First Developer Command Center for the AI-Augmented Engineering Workflow [0.0]
  We present Workstream, an open-source, local-first developer command center that aggregates pull requests, task management, calendar, AI-powered code review, historical review intelligence, repository AI-readiness scoring, and agent observability into a single interface.<n>We describe the system architecture, a novel 5-category AI readiness scoring algorithm, a review intelligence pipeline that mines historical PR reviews for team-specific patterns, and an agent observability layer implementing the Model Context Protocol (MCP), Agent-to-Agent (A2A), and Agent Observability Protocol (AOP)
  arXiv  Detail & Related papers  (2026-04-18T16:24:29Z)
• Developers and Generative AI: A Study of Self-Admitted Usage in Open Source Projects [18.524728732046146]
  We present a taxonomy of 64 different ChatGPT and GitHub Copilot usage tasks, grouped into 7 categories.<n>We show how the usage avenues have been expanded, the extent to which developers perceived such a generative AI usage useful, and whether some concerns occurring more than one year ago are no longer present.
  arXiv  Detail & Related papers  (2026-03-27T10:44:06Z)
• AI Co-Scientist for Ranking: Discovering Novel Search Ranking Models alongside LLM-based AI Agents with Cloud Computing Access [60.37646376282544]
  We present an AI Co-Scientist framework that automates the full search ranking research pipeline.<n>This is the first study in the ranking community to utilize an AI Co-Scientist framework for algorithmic research.
  arXiv  Detail & Related papers  (2026-03-23T09:29:08Z)
• A Survey on Code Generation with LLM-based Agents [61.474191493322415]
  Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm.<n>LLMs are characterized by three core features.<n>This paper presents a systematic survey of the field of LLM-based code generation agents.
  arXiv  Detail & Related papers  (2025-07-31T18:17:36Z)
• The Rise of AI Teammates in Software Engineering (SE) 3.0: How Autonomous Coding Agents Are Reshaping Software Engineering [10.252332355171237]
  This paper introduces AIDev, the first largescale dataset capturing how such agents operate in the wild.<n>Spanning over 456,000 pull requests by five leading agents, AIDev provides an unprecedented empirical foundation for studying autonomous teammates in software development.<n>The dataset includes rich on PRs, authorship, review timelines, code changes, and integration outcomes.
  arXiv  Detail & Related papers  (2025-07-20T15:15:58Z)
• Unified Software Engineering agent as AI Software Engineer [14.733475669942276]
  Large Language Model (LLM) technology has raised expectations for automated coding.<n>In this paper, we seek to understand this question by developing a Unified Software Engineering agent or USEagent.<n>We envision USEagent as the first draft of a future AI Software Engineer which can be a team member in future software development teams involving both AI and humans.
  arXiv  Detail & Related papers  (2025-06-17T16:19:13Z)
• Improving Performance of Commercially Available AI Products in a Multi-Agent Configuration [11.626057561212694]
  Crowdbotics PRD AI is a tool for generating software requirements using AI. GitHub Copilot is an AI pair-programming tool. By sharing business requirements from PRD AI, we improve the code suggestion capabilities of GitHub Copilot by 13.8% and developer task success rate by 24.5%.
  arXiv  Detail & Related papers  (2024-10-29T15:28:19Z)
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents [109.8507367518992]
  We introduce OpenHands, a platform for the development of AI agents that interact with the world in similar ways to a human developer.<n>We describe how the platform allows for the implementation of new agents, safe interaction with sandboxed environments for code execution, and incorporation of evaluation benchmarks.
  arXiv  Detail & Related papers  (2024-07-23T17:50:43Z)
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering [79.07755560048388]
  SWE-agent is a system that facilitates LM agents to autonomously use computers to solve software engineering tasks. SWE-agent's custom agent-computer interface (ACI) significantly enhances an agent's ability to create and edit code files, navigate entire repositories, and execute tests and other programs. We evaluate SWE-agent on SWE-bench and HumanEvalFix, achieving state-of-the-art performance on both with a pass@1 rate of 12.5% and 87.7%, respectively.
  arXiv  Detail & Related papers  (2024-05-06T17:41:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.