用大模型自动生成系统策略，替代人工调参。
Man-Made Heuristics Are Dead. Long Live Code Generators!
- 用大语言模型生成针对具体场景的最优规则
- 在缓存和拥塞控制上超越传统基线表现
- 生成代码可直接集成到Linux内核中
传统系统控制器的策略设计依赖人工手调启发式规则。本文提出PolicySmith框架，利用大语言模型（LLM）驱动的代码生成技术，实现自动化策略搜索。该框架在网页缓存与拥塞控制两个长期存在的系统问题上进行了验证。实验表明，PolicySmith生成的缓存策略在标准开源数据集上优于现有基线；在拥塞控制方面，其生成的策略具备安全性，可直接嵌入Linux内核运行。
原文摘要 · Abstract (English)
Policy design for various systems controllers has conventionally been a manual process, with domain experts carefully tailoring heuristics for the specific instance in which the policy will be deployed. In this paper, we re-imagine policy design via a novel automated search technique fueled by recent advances in generative models, specifically Large Language Model (LLM)-driven code generation. We outline the design and implementation of PolicySmith, a framework that applies LLMs to synthesize instance-optimal heuristics. We apply PolicySmith to two long-standing systems policies - web caching and congestion control, highlighting the opportunities unraveled by this LLM-driven heuristic search. For caching, PolicySmith discovers heuristics that outperform established baselines on standard open-source traces. For congestion control, we show that PolicySmith can generate safe policies that integrate directly into the Linux kernel.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。