"Maybe We Need Some More Examples:" Individual and Team Drivers of Developer GenAI Tool Use

• URL: http://arxiv.org/abs/2507.21280v1
• Date: Mon, 28 Jul 2025 19:05:46 GMT
• Title: "Maybe We Need Some More Examples:" Individual and Team Drivers of Developer GenAI Tool Use
• Authors: Courtney Miller, Rudrajit Choudhuri, Mara Ulloa, Sankeerti Haniyur, Robert DeLine, Margaret-Anne Storey, Emerson Murphy-Hill, Christian Bird, Jenna L. Butler,
• Abstract summary: Despite widespread availability of generative AI tools, developer adoption remains uneven.<n>This unevenness hampers productivity efforts, frustrates management's expectations, and creates uncertainty around the future roles of developers.<n>Our findings imply that widespread organizational expectations for rapid productivity gains without sufficient investment in learning support creates a "Productivity Pressure Paradox"
• Score: 7.989553944867326
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite the widespread availability of generative AI tools in software engineering, developer adoption remains uneven. This unevenness is problematic because it hampers productivity efforts, frustrates management's expectations, and creates uncertainty around the future roles of developers. Through paired interviews with 54 developers across 27 teams -- one frequent and one infrequent user per team -- we demonstrate that differences in usage result primarily from how developers perceive the tool (as a collaborator vs. feature), their engagement approach (experimental vs. conservative), and how they respond when encountering challenges (with adaptive persistence vs. quick abandonment). Our findings imply that widespread organizational expectations for rapid productivity gains without sufficient investment in learning support creates a "Productivity Pressure Paradox," undermining the very productivity benefits that motivate adoption.

Related papers

• The SPACE of AI: Real-World Lessons on AI's Impact on Developers [0.807084206814932]
  We study how developers perceive AI's influence across the dimensions of the SPACE framework: Satisfaction, Performance, Activity, Collaboration and Efficiency.<n>We find that AI is broadly adopted and widely seen as enhancing productivity, particularly for routine tasks.<n>Developers report increased efficiency and satisfaction, with less evidence of impact on collaboration.
  arXiv  Detail & Related papers  (2025-07-31T21:45:54Z)
• Code with Me or for Me? How Increasing AI Automation Transforms Developer Workflows [66.1850490474361]
  We conduct the first academic study to explore developer interactions with coding agents.<n>We evaluate two leading copilot and agentic coding assistants, GitHub Copilot and OpenHands.<n>Our results show agents have the potential to assist developers in ways that surpass copilots.
  arXiv  Detail & Related papers  (2025-07-10T20:12:54Z)
• Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development [65.94639060883475]
  We propose a resource-aware multi-agent system -- Co-Saving.<n>Our key innovation is the introduction of "shortcuts"<n>Compared to the state-of-the-art MAS ChatDev, our method achieves an average reduction of 50.85% in token usage.
  arXiv  Detail & Related papers  (2025-05-28T02:23:53Z)
• What Needs Attention? Prioritizing Drivers of Developers' Trust and Adoption of Generative AI [18.1243411839447]
  We developed a theoretical model of factors influencing trust and adoption intentions towards genAI.<n>We found that genAI's system/output quality, functional value, and goal maintenance significantly influence developers' trust.<n>We provide suggestions to guide future genAI tool design for effective, trustworthy, and inclusive human-genAI interactions.
  arXiv  Detail & Related papers  (2025-05-23T03:05:56Z)
• How do Copilot Suggestions Impact Developers' Frustration and Productivity? [12.302518927205103]
  We propose two theories on the impact of automatic suggestions on frustration and productivity.<n>We will involve at least 32 developers, both experts and novices.
  arXiv  Detail & Related papers  (2025-04-09T11:55:22Z)
• The Impact of Generative AI Coding Assistants on Developers Who Are Visually Impaired [3.2895414694900684]
  We conducted a study where developers who are visually impaired completed a series of programming tasks using a generative AI coding assistant.<n>While participants found the AI assistant beneficial and reported significant advantages, they also highlighted accessibility challenges.<n>Our findings emphasize the need to apply activity-centered design principles to generative AI assistants.
  arXiv  Detail & Related papers  (2025-03-10T22:06:43Z)
• How Performance Pressure Influences AI-Assisted Decision Making [57.53469908423318]
  We show how pressure and explainable AI (XAI) techniques interact with AI advice-taking behavior.<n>Our results show complex interaction effects, with different combinations of pressure and XAI techniques either improving or worsening AI advice taking behavior.
  arXiv  Detail & Related papers  (2024-10-21T22:39:52Z)
• Making Software Development More Diverse and Inclusive: Key Themes, Challenges, and Future Directions [50.545824691484796]
  We identify six themes around the theme challenges and opportunities to improve Software Developer Diversity and Inclusion (SDDI)<n>We identify benefits, harms, and future research directions for the four main themes.<n>We discuss the remaining two themes, Artificial Intelligence & SDDI and AI & Computer Science education, which have a cross-cutting effect on the other themes.
  arXiv  Detail & Related papers  (2024-04-10T16:18:11Z)
• Overwhelmed software developers: An Interpretative Phenomenological Analysis [43.18707677931078]
  We interviewed two software developers who have experienced overwhelm recently. We uncover seven categories of overwhelm (communication, disturbance, organizational, variety, technical, temporal, and positive overwhelm) Participants reported that overwhelm can sometimes be experienced to be positive and pleasant, and it can increase their mental focus, self ambition, and productivity.
  arXiv  Detail & Related papers  (2024-01-05T12:39:08Z)
• Leveraging Large Language Models to Boost Dafny's Developers Productivity [49.64902130083662]
  This paper proposes leveraging Large Language Models (LLMs) to enhance the productivity of Dafny developers. A new Dafny plugin generates suggestions for relevant lemmas that Dafny is unable to discover and use. For the lemmas that cannot be proved automatically, the plugin also attempts to provide accompanying calculational proofs.
  arXiv  Detail & Related papers  (2024-01-01T21:58:13Z)
• Experiential Co-Learning of Software-Developing Agents [83.34027623428096]
  Large language models (LLMs) have brought significant changes to various domains, especially in software development. We introduce Experiential Co-Learning, a novel LLM-agent learning framework. Experiments demonstrate that the framework enables agents to tackle unseen software-developing tasks more effectively.
  arXiv  Detail & Related papers  (2023-12-28T13:50:42Z)
• A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges [23.467373994306524]
  In practice, developers do not accept AI programming assistants' initial suggestions at a high frequency. To understand developers' practices while using these tools, we administered a survey to a large population of developers. We found that developers are most motivated to use AI programming assistants because they help developers reduce key-strokes, finish programming tasks quickly, and recall syntax. We also found the most important reasons why developers do not use these tools are because these tools do not output code that addresses certain functional or non-functional requirements.
  arXiv  Detail & Related papers  (2023-03-30T03:21:53Z)
• Human Decision Makings on Curriculum Reinforcement Learning with Difficulty Adjustment [52.07473934146584]
  We guide the curriculum reinforcement learning results towards a preferred performance level that is neither too hard nor too easy via learning from the human decision process. Our system is highly parallelizable, making it possible for a human to train large-scale reinforcement learning applications. It shows reinforcement learning performance can successfully adjust in sync with the human desired difficulty level.
  arXiv  Detail & Related papers  (2022-08-04T23:53:51Z)

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.