The End of Code Review: Coding Agents Supersede Human Inspection
摘要
文章回顾了自 1976 年 Fagan 代码审查以来，人工 code review 一直是软件开发中的核心质量控制手段。作者指出，基于 LLM 的 coding agents 已具备读取、编写、测试与修复代码的能力，因此已经跨过能力门槛。 论文核心论点是：代码审查的所有既定目标，都可以由 agent 以更低成本和更高吞吐量完成。同时，‘人类仍作为强制 reviewer + agent 写代码’的混合模式被认为不可扩展，也难以提供有效保证，因此可能不是合理演进方向。
荐读理由
用集成式 coding agents（agent-in-loop）替代传统 PR 审查，成本更低且吞吐更高；将团队角色调整为 specifier 与 orchestrator，由此可直接迁移到自己 AI 工程项目的产品开发流水线。
原文
Computer Science > Software Engineering
[Submitted on 11 Jun 2026]
Title:The End of Code Review: Coding Agents Supersede Human Inspection
Authors:Martin Monperrus
View a PDF of the paper titled The End of Code Review: Coding Agents Supersede Human Inspection, by Martin Monperrus
Abstract:Code review has been the primary quality gate in software development since Fagan formalised code inspection in 1976. For five decades, having a human examine and comment on a colleague's changes before merge has been a cornerstone practice at organisations of every size. Coding agents are large language model (LLM)-based autonomous systems capable of reading, writing, testing, and repairing software. We argue that coding agents have crossed a threshold of capability at which traditional human code review is no longer a necessary component of a software quality pipeline. Our argument rests on two claims: every stated goal of code review can be served by agents at lower cost and higher throughput; the naive integration in which agents write code and humans remain the mandatory reviewers is a dead end because it neither provides meaningful assurance nor scales with AI-assisted throughput.
https://doi.org/10.48550/arXiv.2606.13175
arXiv-issued DOI via DataCite (pending registration)
| Subjects: | Software Engineering (cs.SE) |
|---|---|
| Cite as: | arXiv:2606.13175 [cs.SE] |
| (or arXiv:2606.13175v1 [cs.SE] for this version) | |
Submission history
From: Martin Monperrus [view email] [v1] Thu, 11 Jun 2026 10:43:48 UTC (62 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled The End of Code Review: Coding Agents Supersede Human Inspection, by Martin Monperrus
Current browse context:
cs.SE
Change to browse by:
References & Citations
Loading...
BibTeX formatted citation
Data provided by:
Bookmark
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Connected Papers (What is Connected Papers?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
alphaXiv (What is alphaXiv?)
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Hugging Face (What is Huggingface?)
ScienceCast (What is ScienceCast?)
Demos
Replicate (What is Replicate?)
Hugging Face Spaces (What is Spaces?)
TXYZ.AI (What is TXYZ.AI?)
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)
这条对你有帮助吗？