The Cyber Reasoning Challenge (CRC) is an AIxCC-style competition in which student teams design a cyber reasoning system (CRS) to find and patch vulnerabilities in real software targets. Unlike a traditional CTF, teams do not solve challenges by hand. Their CRS must autonomously discover a crashing proof of vulnerability and produce a patch that compiles, preserves the program’s intended behavior, and actually fixes the bug rather than hiding a single crash.

To keep the event focused on system design, we have used the evaluation infrastructure from Team Atlanta, the first-place team in DARPA’s AI Cyber Challenge. Teams therefore do not need to build the evaluation pipeline, scoring, or target-harnessing stack from scratch. They can spend their time on the CRS itself: how it searches, localizes, and repairs bugs.

We also provide a starter kit with two working CRS baseline (codex and claude code). Teams can run it out of the box to understand the workflow, then replace or extend the finder and patcher with their own components.