新闻
KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
arXiv cs.AI · 发布于 · 阅读约3分钟
30秒读懂
- 发生了什么
- KaliBench is a benchmark dataset with 8,504 query-command pairs for evaluating how well LLMs translate natural language into executable Kali Linux cybersecurity tool commands.
- 为何重要
- Security engineers and ML researchers building or evaluating AI systems that must generate precise command-line instructions for penetration testing and security analysis workflows.
- 注意
- No open-weight model exceeded 42% exact-command accuracy without tool hints, suggesting current LLMs struggle with CLI syntax precision despite improvements from fine-tuning.
- agent
- agentic
- llm
- tool use
- edge
这条新闻背后的模式
每个模式都讲清楚技术如何运作、何时值得投入，以及在哪里会失效。
The Agent Architect
每周一个模式、一个权衡、一个生产事故案例。为构建智能体系统的人准备的每周简报。
每周一封邮件,一键退订。您的地址仅用于发送简报。