发表机构
University of California, Davis; Oregon State University（加州大学戴维斯分校; 俄勒冈州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
Vibe-GUIDE通过基于功能模块的实时可操作图界面，增强智能体编程中开发者的项目理解与监督能力，实验表明其优于仅聊天基线。
AI 中文摘要
在智能体编程中，开发者从自己实现变更转变为指定意图、评估智能体的工作并做出批准决策。然而，委托实现可能会引入认知债务，随着时间推移侵蚀项目理解，限制开发者提供监督的能力。在本工作中，我们研究了持久共享表示在支持项目理解和编码智能体监督中的作用。我们提出了Vibe-GUIDE，一种围绕按功能模块组织的结构化、实时、可操作且自适应的图表示构建的智能体编程界面。我们在随机受试者间研究中评估了我们的界面，比较了16名开发者使用我们的界面或仅聊天基线完成三项累积编码任务的情况。我们发现Vibe-GUIDE可以支持项目理解和持续的任务表现，同时保持开发者在监督中的认知参与。这些发现表明，持久共享表示可以补充自然语言交互，并帮助开发者在项目演进时维持理解，以监督智能体生成的变更。
英文摘要
In agentic coding, developers shift from implementing changes themselves to specifying intent, evaluating the agent's work, and making approval decisions. However, delegating implementation can introduce cognitive debt that erodes project comprehension over time, constraining developers' ability to provide oversight. In this work, we investigate the role of persistent shared representations in supporting project comprehension and oversight of coding agents. We present Vibe-GUIDE, an agentic coding interface built around a structural, live, manipulable, and adaptive graph representation organized by functional modules. We evaluated our interface in a randomized between-subjects study comparing how 16 developers completed three cumulative coding tasks using our interface or a Chat-only baseline. We found that Vibe-GUIDE can support project comprehension and sustained task performance while keeping developers cognitively involved in oversight. These findings show how persistent shared representations can complement natural-language interaction and help developers maintain the understanding needed to oversee agent-generated changes as projects evolve.
Comments14 pages, 3 figures, 4 tables
