Rethinking Software Engineering for Agentic AI Systems

• URL: http://arxiv.org/abs/2604.10599v1
• Date: Sun, 12 Apr 2026 12:08:53 GMT
• Title: Rethinking Software Engineering for Agentic AI Systems
• Abstract summary: Large language models and agentic AI systems have created an unprecedented abundance of automatically generated code.<n>This paper examines whether the discipline should be reoriented around orchestration, verification, and human-AI collaboration.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The rapid proliferation of large language models (LLMs) and agentic AI systems has created an unprecedented abundance of automatically generated code, challenging the traditional software engineering paradigm centered on manual authorship. This paper examines whether the discipline should be reoriented around orchestration, verification, and human-AI collaboration, and what implications this shift holds for education, tools, processes, and professional practice. Drawing on a structured synthesis of relevant literature and emerging industry perspectives, we analyze four key dimensions: the evolving role of the engineer in agentic workflows, verification as a critical quality bottleneck, observed impacts on productivity and maintainability, and broader implications for the discipline. Our analysis indicates that code is transitioning from a scarce, carefully crafted artifact to an abundant and increasingly disposable commodity. As a result, software engineering must reorganize around three core competencies: effective orchestration of multi-agent systems, rigorous verification of AI-generated outputs, and structured human-AI collaboration. We propose a conceptual framework outlining the transformations required across curricula, development tooling, lifecycle processes, and governance models. Rather than diminishing the role of engineers, this shift elevates their responsibilities toward system-level design, semantic validation, and accountable oversight. The paper concludes by highlighting key research challenges, including verification-first lifecycles, prompt traceability, and the long-term evolution of the engineering workforce.

Related papers

• Educating the Agentic Engineer: Curricula, Collaboration, and Continuous Learning in the AI Era [0.0]
  Generative and agentic artificial intelligence (AI) are reconfiguring software and systems engineering from a discipline centered on human authorship to one focused on directing, verifying, and governing autonomous systems.<n>This article presents an integrative conceptual synthesis across engineering education, computing education, human-AI interaction, human factors, and the learning sciences to derive an evidence-grounded educational architecture for this archetype.
  arXiv  Detail & Related papers  (2026-07-31T16:45:36Z)
• From Determinism to Delegation: AI-Native Software Engineering and the Evolution of the Agentic Engineer [0.0]
  Software engineering is experiencing its most significant transformation since the emergence of high-level programming languages.<n>This paper argues that AI-Native Software Engineering is a paradigm shift rather than a mere tooling advance.<n>We define core mechanisms of autonomous agents, including reasoning-acting loops, context engineering, tool use, memory, behavioral drift, and compositional error.
  arXiv  Detail & Related papers  (2026-06-27T07:43:43Z)
• Human-AI Collaboration and the Transformation of Software Engineering Work [0.0]
  The integration of Generative AI (GenAI) and Agentic AI into software development is reconfiguring software engineering.<n>We map which traditional activities are being automated, which are being augmented, and which are newly emerging.<n>We derive nine empirically testable propositions and articulate implications for theory, industry workforce transformation, university curricula, and organizational leadership.
  arXiv  Detail & Related papers  (2026-06-02T09:36:39Z)
• Artificial Intelligence as a Catalyst for Innovation in Software Engineering [0.0]
  This article explores how AI serves as a powerful catalyst for enhancing agility and fostering innovation.<n>The integration of AI (specifically through Machine Learning (ML) and Natural Language Processing (NLP))facilitates the automation of tedious tasks.
  arXiv  Detail & Related papers  (2026-03-11T17:20:30Z)
• When Code Becomes Abundant: Redefining Software Engineering Around Orchestration and Verification [1.217503190366097]
  We argue that Software Engineering must redefine itself around intent articulation, architectural control, and verification.<n>This shift introduces accountability collapse as a central risk and requires fundamental changes to research priorities, educational curricula, and industrial practices.
  arXiv  Detail & Related papers  (2026-02-04T18:18:53Z)
• EmboCoach-Bench: Benchmarking AI Agents on Developing Embodied Robots [68.29056647487519]
  Embodied AI is fueled by high-fidelity simulation and large-scale data collection.<n>However, this scaling capability remains bottlenecked by a reliance on labor-intensive manual oversight.<n>We introduce textscEmboCoach-Bench, a benchmark evaluating the capacity of LLM agents to autonomously engineer embodied policies.
  arXiv  Detail & Related papers  (2026-01-29T11:33:49Z)
• Advances and Frontiers of LLM-based Issue Resolution in Software Engineering: A Comprehensive Survey [59.3507264893654]
  Issue resolution is a complex Software Engineering task integral to real-world development.<n> benchmarks like SWE-bench revealed this task as profoundly difficult for large language models.<n>This paper presents a systematic survey of this emerging domain.
  arXiv  Detail & Related papers  (2026-01-15T18:55:03Z)
• Revisiting Software Engineering Education in the Era of Large Language Models: A Curriculum Adaptation and Academic Integrity Framework [0.0]
  This paper proposes a theoretical framework for analyzing how generative AI alters core software engineering competencies.<n> Attention is given to computer engineering programs in Turkey, where centralized regulation, large class sizes, and exam-oriented assessment practices amplify these challenges.
  arXiv  Detail & Related papers  (2026-01-06T22:41:47Z)
• A Survey of Vibe Coding with Large Language Models [93.88284590533242]
  "Vibe Coding" is a development methodology where developers validate AI-generated implementations through outcome observation.<n>Despite its transformative potential, the effectiveness of this emergent paradigm remains under-explored.<n>This survey provides the first comprehensive and systematic review of Vibe Coding with large language models.
  arXiv  Detail & Related papers  (2025-10-14T11:26:56Z)
• Reflexive Prompt Engineering: A Framework for Responsible Prompt Engineering and Interaction Design [0.0]
  Article examines how strategic prompt engineering can embed ethical and legal considerations directly into AI interactions.<n>It proposes a framework for responsible prompt engineering that encompasses five interconnected components.<n>The analysis reveals that effective prompt engineering requires a delicate balance between technical precision and ethical consciousness.
  arXiv  Detail & Related papers  (2025-04-22T18:51:32Z)
• Generative AI and Empirical Software Engineering: A Paradigm Shift [9.284024538100063]
  This vision paper examines how the integration of large language models into software engineering disrupts established research paradigms.<n>We discuss how it transforms the phenomena we study, the methods and theories we rely on, the data we analyze, and the threats to validity that arise in dynamic AI-mediated environments.<n>Our aim is to help the empirical software engineering community adapt its questions, instruments, and validation standards to a future in which AI systems are not merely tools, but active collaborators shaping software engineering and its study.
  arXiv  Detail & Related papers  (2025-02-12T04:13:07Z)
• Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering [51.31836988300326]
  Verifier engineering is a novel post-training paradigm specifically designed for the era of foundation models. We systematically categorize the verifier engineering process into three essential stages: search, verify, and feedback.
  arXiv  Detail & Related papers  (2024-11-18T12:04:52Z)
• Technology Readiness Levels for Machine Learning Systems [107.56979560568232]
  Development and deployment of machine learning systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. We have developed a proven systems engineering approach for machine learning development and deployment. Our "Machine Learning Technology Readiness Levels" framework defines a principled process to ensure robust, reliable, and responsible systems.
  arXiv  Detail & Related papers  (2021-01-11T15:54:48Z)
• Technology Readiness Levels for AI & ML [79.22051549519989]
  Development of machine learning systems can be executed easily with modern tools, but the process is typically rushed and means-to-an-end. Engineering systems follow well-defined processes and testing standards to streamline development for high-quality, reliable results. We propose a proven systems engineering approach for machine learning development and deployment.
  arXiv  Detail & Related papers  (2020-06-21T17:14:34Z)

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.