Newest papers

RegoMender: A Multi-agent Framework for Automated Rego Policy Repair

Ruijie Zhang, Huaxiao Yin, Li Hu, Fanqi Kong, Haozhe Liang, Shaoyin Cheng, Kun Zhang, Bibo Tu · 2026 · IEEE/ACM International Conference on Automated Software Engineering (ASE)

DOI: 10.1145/3832783.3837490 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Политика-как-код (PaC) появилась как фундаментальная парадигма в облачных системах. Тем не менее, ремонт политики Rego остается сложным из-за их строгой синтаксиса, декларативной семантики и специфических требований к проверке. Существующие методы автоматизированного программного ремонта (APR) в основном разработаны для основных языков и борьбы с уникальной логикой политики и рабочими процессами ремонта Rego. Таким образом, ремонт политики Rego остается ручным процессом, управляемым одним испытанием и ошибкой. Чтобы решить этот вопрос, мы вводим RegoBench, первый автоматизированный рейтинг политики Rego, включающий в себя 1,159 дефектов реального мира, и предлагаем RegoMender, ориентированную на обратную связь многоагентную структуру.

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Process management, Business, Software engineering, Government (linguistics), Key (lock)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange