用大模型生成可验证的系统调度策略，提升资源利用效率。
Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search
- 将决策逻辑隔离为无状态函数，限制大模型输出范围
- 在三个场景中实现最高4.9倍成本节省、2倍缓存误失率降低
- 适合需要安全可靠自动化调优的系统工程师
系统资源管理主要依赖人工设计的启发式规则。但硬件异构性和工作负载多样性要求针对特定部署实例定制规则，导致手工设计成本高且难以扩展。本文探索利用大模型合成系统启发式规则。主要挑战在于确保生成规则执行安全、与系统正确集成且性能强劲。我们提出Vulcan框架，通过识别对大模型友好的接口，将核心决策逻辑与其余实现分离。使用Vulcan时，大模型仅生成简单无状态的决策函数，而可信的运行时抽象提供丰富的派生统计信息，支持有意义的策略探索，避免系统集成错误。为保障执行安全，大模型在受限语言Anvil中生成规则，该语言通过构造保证关键属性。我们在三个经典领域评估Vulcan，结果显示：在抢占式虚拟机调度中最高节省4.9倍成本，缓存淘汰策略误失率降低最多2倍，分层内存系统应用性能提升最高10%，全程确保执行安全。
原文摘要 · Abstract (English)
Systems resource management tasks rely primarily on hand-designed heuristics. However, growing hardware heterogeneity and workload diversity require heuristics specialized to particular deployment instances, making manual design expensive and difficult to scale. In this paper, we explore how to synthesize systems heuristics using LLMs. The main challenge is ensuring that generated heuristics execute safely, integrate correctly with the surrounding system, and still achieve strong performance. We propose Vulcan, a framework that identifies LLM-friendly interfaces that isolate core decision logic from the rest of the implementation. With Vulcan, LLM-generated code is restricted to simple stateless decision functions, while trusted runtime abstractions provide rich derived statistics for meaningful policy exploration without system-integration bugs. To ensure execution safety, LLMs synthesize heuristics in a restricted language, Anvil, that guarantees important properties by construction. We evaluate Vulcan across three well-studied domains and demonstrate up to 4.9x higher savings for spot-VM scheduling, up to 2x lower miss ratios for cache eviction, and up to 10% higher application performance for tiered-memory systems, while ensuring execution safety throughout.
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。