← Back to all news
arXiv AI By Ruijie Zhang, Huaxiao Yin, Li Hu, Fanqi Kong, Haozhe Liang, Shaoyin Cheng, Kun Zhang, Bibo Tu

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

Read the original on arXiv AI →

RegoMender is a multi‑agent framework that automates the repair of Rego policies, a key component of Policy‑as‑Code in cloud‑native systems. It uses a shared blackboard and atomic toolkit to dynamically apply patching, rewriting, or rollback actions, achieving high syntactic (82.9%) and semantic (77.9%) success rates on the newly introduced RegoBench benchmark of 1,159 real‑world defects. The system also generalizes to other languages such as HCL and SQL, repairing 86.4% of 132 real‑world CVE vulnerabilities, thereby demonstrating robustness and practical security value.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 1

Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study

The paper presents a systematic analysis of five state‑of‑the‑art automated program repair agents, tracing their decision‑making across 500 real‑world repair tasks. It finds that while the agents perform well on simple fixes, they struggle with logic‑intensive bugs, often producing verbose, overfitted patches that pass tests without addressing root causes. Key bottlenecks identified include poor test generation, limited regression test selection, and reliance on primitive tooling without access to debuggers or advanced program analysis tools.

By Ira Ceka, Hailie Mitchell, Saurabh Pujar, Luca Buratti, Shyam Ramji, Junfeng Yang, Gail Kaiser, Baishakhi Ray
llmsagentsbenchmarks
More like this →