Code Review is a Conversation: Toward Conversational AI Review Assistants

2026-07-24

AI Summary

This work addresses a critical limitation in current AI-powered code review tools, which reduce the review process to single-round comments and overlook the inherently dialogic nature of real-world code reviews—characterized by multi-turn interaction, negotiation, and knowledge exchange. To bridge this gap, the paper introduces the first conversational AI code review paradigm, featuring a context-aware dialogue agent capable of proactively asking questions, responding to developer explanations, summarizing issues, and judiciously escalating to human reviewers when appropriate. Integrating techniques from dialogue systems, natural language generation, and software engineering knowledge modeling, the approach emphasizes collaborative sensemaking between humans and AI. The study further advocates for a new evaluation framework centered on conversational competence, laying theoretical and methodological foundations for next-generation AI code review tools that support multi-turn interaction, knowledge transfer, and collective decision-making.

Abstract

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.

Problem

• code review
• conversational AI
• human-AI interaction
• software maintenance
• pull requests

Innovation

• conversational AI
• code review
• human-AI collaboration
• sensemaking
• interactive assistants