AI 中文总结
研究指出当前代码审查多为一次性注释任务，忽略其对话本质。主张构建对话式人工智能审查助手，能互动交流、提问解答等。还概述了研究议程，将AI代码审查从自动化注释转变为集成前人机协作理解，带来范式转变。
AI 中文摘要
基于人工智能的代码审查工具越来越有望帮助开发人员检查拉取请求、识别缺陷并提高代码质量。然而，当前大多数方法将代码审查视为一次性注释任务：给定一个差异，系统会生成警告或建议。这种框架忽略了现代代码审查的一个核心特性：审查是一场对话。人类审查者不仅对代码进行注释，还会提问、解释期望、协商设计权衡、要求提供证据、传授项目知识、记录基本原理，并共同决定一个更改是否足以集成。在这篇展望论文中，我们主张使用对话式人工智能审查助手：即作为交互式伙伴而非静态注释生成器参与代码审查的系统。这样的助手应识别何时需要对话、提出有根据的问题、回应开发人员的解释、总结未解决的问题、帮助记录基本原理，并知道何时弃权或升级给人类审查者。这种范式转变也需要新颖的评估方法。我们概述了一个研究议程，用于研究审查对话、设计对话式人工智能审查功能，并评估它们对软件演化和维护的影响。我们的愿景将人工智能代码审查从自动化注释重新定义为集成前的人机协作理解。
英文摘要
AI-based code review tools increasingly promise to help developers inspect pull requests, identify defects, and improve code quality. Yet most current approaches frame code review as a one-shot commenting task: given a diff, the system produces warnings or suggestions. This framing overlooks a central property of modern code review: review is a conversation. Human reviewers do not merely comment on code; they ask questions, explain expectations, negotiate design trade-offs, request evidence, transfer project knowledge, document rationale, and collectively decide whether a change is good enough to integrate. In this vision paper, we argue for conversational AI review assistants: systems that participate in code review as interactive partners rather than static comment generators. Such assistants should identify when conversation is needed, ask grounded questions, respond to developer explanations, summarize unresolved issues, help capture rationale, and know when to abstain or escalate to human reviewers. Such a paradigm shift requires novel evaluation methodologies as well. We outline a research agenda for studying review conversations, designing conversational AI review capabilities, and evaluating their impact on software evolution and maintenance. Our vision reframes AI code review from automated commenting to human-AI sensemaking before integration.
CommentsAccepted at ICSME 2026 in the Visions and Emerging Results Track
