The State of Generative AI in Software Development: Insights from Literature and a Developer Survey

• URL: http://arxiv.org/abs/2603.16975v1
• Date: Tue, 17 Mar 2026 12:59:59 GMT
• Title: The State of Generative AI in Software Development: Insights from Literature and a Developer Survey
• Abstract summary: This study integrates a literature review with a survey of 65 software developers.<n>Results show that GenAI exerts its highest impact in design, implementation, testing, and documentation.<n>79 % of survey respondents use GenAI daily, preferring browser-based Large Language Models over alternatives integrated directly in their development environment.
• Score: 4.097943522310277
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Generative Artificial Intelligence (GenAI) rapidly transforms software engineering, yet existing research remains fragmented across individual tasks in the Software Development Lifecycle. This study integrates a systematic literature review with a survey of 65 software developers. The results show that GenAI exerts its highest impact in design, implementation, testing, and documentation, where over 70 % of developers report at least halving the time for boilerplate and documentation tasks. 79 % of survey respondents use GenAI daily, preferring browser-based Large Language Models over alternatives integrated directly in their development environment. Governance is maturing, with two-thirds of organizations maintaining formal or informal guidelines. In contrast, early SDLC phases such as planning and requirements analysis show markedly lower reported benefits. In a nutshell, GenAI shifts value creation from routine coding toward specification quality, architectural reasoning, and oversight, while risks such as uncritical adoption, skill erosion, and technical debt require robust governance and human-in-the-loop mechanisms.

Related papers

• Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI [42.44812101223683]
  This paper presents a systematic approach using Claude agentic AI on real-world project-scheduling workloads in a high-performance computing environment.<n>Testing runtime reduced from 1,298 seconds to under 200 seconds without changing outputs, saving four million core-hours (NZ$320,000) annually.
  arXiv  Detail & Related papers  (2026-08-19T22:48:46Z)
• On Automated and Explainable Provenance of AI-Generated Code [56.818202904805446]
  We argue that the next generation of CodeGenAI tools must be built on a foundation of explainable provenance.<n>We describe a research program combining large-scale empirical studies with post-hoc causal and interpretability techniques.
  arXiv  Detail & Related papers  (2026-08-03T14:50:31Z)
• From Early Adoption to Sustained Use: Understanding GenAI Usage Among Software Developers in Italian SMEs [41.13700651273253]
  This study investigates factors associated with developers' intentions to continue using GenAI tools.<n>In voluntary professional contexts, sustained use is driven primarily by individual-level factors rather than by social and organisational support.
  arXiv  Detail & Related papers  (2026-05-25T15:47:46Z)
• At What Cost? Software Developers' Well-Being in the Age of GenAI [6.363930998744341]
  Generative Artificial Intelligence (GenAI) is rapidly reshaping software development.<n>Excessive focus on such dimensions risks overlooking the critical implications for developer well-being.<n>GenAI tools can amplify cognitive load, introduce new forms of oversight labor, and escalate expectations around output and pace.
  arXiv  Detail & Related papers  (2026-05-21T11:35:31Z)
• Prompting in Practice: Investigating Software Developers' Use of Generative AI Tools [17.926187565860232]
  The integration of generative artificial intelligence (GenAI) tools has fundamentally transformed software development.<n>This study presents a systematic investigation of how software engineers integrate GenAI tools into their professional practice.<n>We surveyed 91 software engineers, including 72 active GenAI users, to understand AI usage patterns throughout the development process.
  arXiv  Detail & Related papers  (2025-10-07T15:02:22Z)
• 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)
• Survey of GenAI for Automotive Software Development: From Requirements to Executable Code [4.909409341455637]
  Automotive software development is considered to be a significant area for GenAI adoption.<n>Three GenAI-related technologies are covered within the state-of-art: Large Language Models (LLMs), Retrieval Augmented Generation (RAG), Vision Language Models (VLMs)
  arXiv  Detail & Related papers  (2025-07-20T16:21:51Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• Generative AI for Software Architecture. Applications, Challenges, and Future Directions [6.883775050854466]
  We aim to systematically synthesize the use, rationale, contexts, usability, and future challenges of GenAI in software architecture.<n>Our review identified significant adoption of GenAI for architectural decision support and architectural reconstruction.
  arXiv  Detail & Related papers  (2025-03-17T15:49:30Z)
• From Defects to Demands: A Unified, Iterative, and Heuristically Guided LLM-Based Framework for Automated Software Repair and Requirement Realization [44.99833362998488]
  This manuscript signals a new era in the integration of artificial intelligence with software engineering.<n>We present a formalized, iterative methodology proving that AI can fully replace human programmers in all aspects of code creation and refinement.
  arXiv  Detail & Related papers  (2024-12-06T14:54:21Z)
• Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement [62.94719119451089]
  Lingma SWE-GPT series learns from and simulating real-world code submission activities. Lingma SWE-GPT 72B resolves 30.20% of GitHub issues, marking a significant improvement in automatic issue resolution.
  arXiv  Detail & Related papers  (2024-11-01T14:27:16Z)
• Generative Artificial Intelligence for Software Engineering -- A Research Agenda [8.685607624226037]
  We conducted a literature review and focus groups for a duration of five months to develop a research agenda on GenAI for Software Engineering. Our results show that it is possible to explore the adoption of GenAI in partial automation and support decision-making in all software development activities. Common considerations when implementing GenAI include industry-level assessment, dependability and accuracy, data accessibility, transparency, and sustainability aspects associated with the technology.
  arXiv  Detail & Related papers  (2023-10-28T09:14:39Z)
• Investigating Explainability of Generative AI for Code through Scenario-based Design [44.44517254181818]
  generative AI (GenAI) technologies are maturing and being applied to application domains such as software engineering. We conduct 9 workshops with 43 software engineers in which real examples from state-of-the-art generative AI models were used to elicit users' explainability needs. Our work explores explainability needs for GenAI for code and demonstrates how human-centered approaches can drive the technical development of XAI in novel domains.
  arXiv  Detail & Related papers  (2022-02-10T08:52:39Z)

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.