arXiv cs.AI· Ruijie Zhang, Huaxiao Yin, Li Hu, Fanqi Kong, Haozhe Liang, Shaoyin Cheng, Kun Zhang, Bibo Tu·· 13 小时前AI 评分31
RegoMender：面向 Rego 策略自动修复的多智能体框架
RegoMender: A Multi-agent Framework for Automated Rego Policy Repair
AI 导读
RegoMender 是一个反馈引导的多智能体框架，通过共享黑板和原子工具包动态执行打补丁、重写或回滚，用于自动修复 Rego 策略。团队同时构建了首个 Rego 策略自动修复基准 RegoBench，含 1,159 个真实缺陷；RegoMender 在 RegoBench 上语法与基于测试的语义成功率分别为 82.9% 和 77.9%，超出最强基线 13.4%。
正文 · 原文
Abstract:Policy-as-Code (PaC) has emerged as a foundational paradigm in cloud-native systems. However, repairing Rego policies remains challenging due to their strict syntax, declarative semantics, and specific verification requirements. Existing automated program repair (APR) methods are mainly designed for mainstream languages and struggle to accommodate the unique policy logic and repair workflows of Rego. Thus, Rego policy repair remains a manual process driven by trial and error. To address this, we introduce RegoBench, the first automated Rego policy benchmark comprising 1,159 real-world defects, and propose RegoMender, a feedback-guided multi-agent framework. Collaborating via a shared blackboard and an atomic toolkit, RegoMender dynamically executes patching, rewriting, or rolling back, to resolve complex repair scenarios. Evaluated on RegoBench, RegoMender achieves syntactic and test-based semantic success rates of 82.9\% and 77.9\%, respectively, outperforming the strongest baseline by 13.4\%. Unlike other approaches whose performance drops in complex scenarios, RegoMender maintains effectiveness across single-step and chained repair tasks. Furthermore, it generalizes strongly across HCL and SQL and achieves an 86.4\% repair rate on 132 real-world CVE vulnerabilities, proving its robustness and practical utility for security.
| Comments: | 13 pages, 5 figures, accepted to ASE 2026, research Track |
| Subjects: | Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Programming Languages (cs.PL) |
| Cite as: | arXiv:2610.29456 [cs.SE] |
| (or arXiv:2610.29456v1 [cs.SE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29456 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Li Hu [view email]
[v1]
Wed, 21 Oct 2026 09:14:12 UTC (1,112 KB)
来源：arXiv cs.AI · arxiv.org