AI自主设计计算机系统，效率超人类专家且可解释。
Glia: A Human-Inspired AI for Automated Systems Design and Optimization
- 用多智能体协作模拟人类思维，分角色负责推理、实验与分析。
- 在分布式GPU集群上实现人类专家级的请求调度与自动扩缩容方案。
- 生成可解释的设计过程，适合系统优化与AI辅助研发场景。
能否让AI像人类专家一样自主设计计算机系统机制？我们提出Glia，一种面向网络化系统的AI架构，利用大语言模型（LLMs）构建类人多智能体工作流。每个智能体专注于推理、实验与分析，通过评估框架将抽象推理与实证反馈结合。不同于以往仅优化黑箱策略的机器学习方法，Glia能生成可解释的设计并展现其推理过程。应用于支持大模型推理的分布式GPU集群时，它生成了新的请求路由、调度与自动扩缩容算法，在显著更短时间内达到人类专家水平，并揭示了负载行为的新见解。结果表明，结合推理型大模型与结构化实验，可生成创造性且可理解的复杂系统设计方案。
原文摘要 · Abstract (English)
Can AI autonomously design mechanisms for computer systems on par with the creativity and reasoning of human experts? We present Glia, an AI architecture for networked systems design that uses large language models (LLMs) in a human-inspired multi-agent workflow. Each agent specializes in reasoning, experimentation, and analysis, collaborating through an evaluation framework that grounds abstract reasoning in empirical feedback. Unlike prior ML-for-systems methods that optimize black-box policies, Glia generates interpretable designs and exposes its reasoning. When applied to a distributed GPU cluster for LLM inference, it produces new algorithms for request routing, scheduling, and auto-scaling that perform at human-expert levels in significantly less time, while yielding novel insights into workload behavior. Our results suggest that combining reasoning LLMs with structured experimentation, an AI can produce creative and understandable designs for complex systems problems.
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。