网络自动化中的前沿大语言模型陷阱
The Frontier LLM Trap in Network Automation
浏览论文内容
中文总结 AI 辅助
针对网络自动化中前沿大语言模型成本高、依赖AI提供商等问题，提出用模糊测试与验证构建离线循环生成规则，指导小型模型实现低成本、可审计的自动化，且知识在网络本地积累。
中文摘要 AI 辅助
大型大语言模型（LLM）是网络自动化的强大工具，但成本高昂、服务速度慢、难以审计、对单个网络的适配性差，且会造成对少数AI提供商的长期依赖。现有替代方案存在不足：小型开源模型成本较低但可靠性差，而确定性脚本和验证虽可控但难以构建和维护。我们提出一种折中方案：由模糊测试和验证组成的离线循环可发现小型模型反复出现的错误，随后将生成的网络知识表述为显式逻辑规则。在生产环境中，这些规则指导小型模型完成配置转换等任务，从而实现更廉价、延迟更低、可审计且更易适配特定网络的自动化。更关键的是，网络知识和运营经验会在其应属的网络本身积累，而非托管在租用的服务中。
英文摘要
Large LLMs are powerful tools for network automation, but they are expensive, slow to serve, hard to audit, poorly tailored to individual networks, and create long-term dependencies on a small number of AI providers. Existing alternatives fall short: small open-source models are cheaper but unreliable, while deterministic scripts and verification are controllable but hard to build and maintain. We propose a middle ground. An offline loop composed of fuzzing and validation discovers the recurring mistakes small models make, then resulting networking knowledge is expressed as explicit logic rules. In production, these rules guide a small model on tasks such as configuration translation, yielding automation that is cheaper, lower-latency, auditable, and easier to adapt to a specific network. More critically, network knowledge and operational experience stay and are accumulated where they belong, the network itself, not a rented service.
