English(EN) Can Agentic Code Review Catch Vulnerabilities Before They Are Merged?

新的基准SecPRBench测试AI代码审查在安全漏洞方面的能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

一个名为SecPRBench的新基准已被开发出来，用于评估AI代理在代码合并前识别安全漏洞的有效性。该基准利用了来自Firefox、V8和OpenSSL等关键系统的真实引入错误提交，而不是后来的修复。对八个前沿模型的初步测试显示，召回率从32.5%到78.1%不等，其中Grok 4.6和GPT-6 Sol表现最佳。研究还强调了代理行为的差异，例如OpenAI的Codex Security更频繁地弃权，而Anthropic的Defending Code harness以更高的成本提高了召回率。 AI

影响该基准可以加速开发更强大的AI安全工具，用于软件开发。

排序理由该项目是一篇研究论文，介绍了一个用于评估AI代理在代码安全方面的新基准。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇研究论文，介绍了一个用于评估AI代理在代码安全方面的新基准。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Yihan Yang, Chenyuan Yang, Zijie Zhao, Anh Nguyen Hoang, Ziqi Zhang, Weidong Wang, Zhiheng Lyu, Lingming Zhang · 2026-10-27 04:00

代理代码审查能否在漏洞合并前被发现？

arXiv:2610.33509v1 Announce Type: cross Abstract: LLM agents have been increasingly adopted for security-focused code review, but existing benchmarks mostly derive the reviewed changes from their later fixes instead of the real-world bug-introducing commits. In this paper, we pre…

本文如何被排名

报道来源 [1]

代理代码审查能否在漏洞合并前被发现？

相关实体

相关话题