PatchIsland: Orchestration of LLM Agents for Continuous Vulnerability Repair

Jul 17, 2026

PatchIsland is a system that orchestrates an ensemble of diverse large language model (LLM) agents to automate vulnerability repair within continuous fuzzing pipelines. In the official AIxCC competition, PatchIsland operated fully autonomously and achieved a 72.1% repair rate, successfully patching 31 out of 43 vulnerabilities. The system also introduces a two-phase patch-based deduplication process to address duplicate crashes and patches, improving robustness in noisy, real-world environments.

Why it matters: This work demonstrates a significant advance in automated software vulnerability repair, showing that LLM agents can autonomously and effectively patch real-world vulnerabilities in continuous integration settings.

Full story at: arXiv Cryptography and Security ↗