arXiv cs.AI· Xinyuan Song, Hasibul Haque, Jay Somasundaram, Ryan Turner, Bowen Zhu, Liang Zhao·· 4 小时前AI 评分37
CIVER：基于因果干预验证的可靠代码审查框架
CIVER: Causal Intervention Verification for Reliable Code Review
AI 导读
CIVER 是一个基于因果干预的框架，用于从 LLM 代码审查结果中区分真实缺陷与误报。它由评估发现的审查模块、生成修复导向扰动的干预模块和打分审查可靠性的验证器模块组成，通过 expert iteration 联合优化。在 SWE-Review-Bench 上，CIVER 通过针对性修复正确识别了 77% 的真实缺陷，并能跨仓库泛化、提升 coding agent 的任务成功率。
正文 · 原文
Abstract:Code review is essential for maintaining software repositories by identifying defects, improving code quality, and supporting reliable software evolution. With the growing adoption of LLM-based coding agents, an increasing number of code contributions and repository changes are generated by these agents. Consequently, LLM-based code review agents are becoming increasingly prevalent to evaluate these contributions and maintain software quality. However, LLM reviewers often generate lengthy reviews containing numerous potential issues, many of which are false positives or lack sufficient evidence. These unreliable reviews can mislead developers and downstream coding agents, motivating the need to distinguish actionable findings from unsupported claims. We propose CIVER, a causal intervention-based framework that identifies the core issues underlying code-review findings and distinguishes genuine defects from false positives. CIVER integrates three modules: a review module assesses findings, an intervention module generates repair-oriented perturbations, and a verifier module scores review reliability. Through joint optimization via expert iteration, the three modules identify genuine defects by responding to targeted repairs while remaining stable under unrelated changes. Extensive experiments on SWE-Review-Bench demonstrate that CIVER correctly identifies 77% of genuine defects through targeted repairs. Cross-project and downstream repair evaluations further demonstrate that CIVER generalizes across repositories and improves coding agents' task success rates, highlighting its effectiveness for reliable automated code review.
| Comments: | WWW 2026 |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.36010 [cs.SE] |
| (or arXiv:2610.36010v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.36010 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tide Song [view email]
[v1]
Mon, 26 Oct 2026 16:29:40 UTC (1,730 KB)
来源：arXiv cs.AI · arxiv.org