Feyospace-v1：七人团队如何训练前沿网络安全模型
原标题：Paper page - Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models
AI 摘要
该论文提出 Feyospace-v1，一个以数据为中心的后训练框架，通过 Choulea、SkyReal、Hongzwang、PSBreakup、Kreator 五个系统解决可执行环境成本、多轮监督与教师模型获取等瓶颈。团队构建可重置的代码、漏洞、CTF、内核、固件等环境，经执行验证与证据审计后保留 164,269 条轨迹用于长上下文监督微调。三个检查点在 CyberGym 上平均提升 23.76%，在 CTF 套件上提升 10.49%，Feyospace-s1 以 63.24% 成功率排名第 10，并在同参数规模开源模型中排名第 1。论文称这是首个七人独立团队训练出领先智能体网络安全能力开源模型的端到端演示。
正文节选
Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models Abstract A data-centric framework with specialized systems for reasoning analysis, cost reduction, and execution verification enables small teams to train open-weight cyber agents that achieve top-tier performance on benchmark suites. Training capable cyber agents is often treated primarily as a problem of model scale, yet open-weight post-training is constrained more directly by the cost of executable environments, reliable