用AI生成高效算法，解决系统设计中创意不足的问题
MetaMuse: Algorithm Generation via Creative Ideation
- 通过可量化的性能空间引导，让AI生成多样且实用的算法
- 在缓存替换中减少35.76%缓存缺失，在装箱问题中降低30.93%资源使用
- 适合需要高效率算法的系统工程师和自动化设计研究者
系统算法设计仍具挑战性，因其解空间不连续，常导致工程师依赖通用启发式方法而影响性能。我们研究大语言模型（LLM）是否能实际驱动算法生成，发现其倾向于已知通用设计，难以实现创造性突破。为此，我们提出MetaMuse框架，基于三项自反思原则：（1）在可度量的性能空间中评估解的多样性与实用性，而非抽象想法空间；（2）通过外部刺激引导生成，而非内部随机性；（3）采用路径点推理构建可执行解，而非自由链式思考。在某全球云服务商的两个关键在线问题上进行评估，结果表明MetaMuse能生成高性能方案：在缓存替换任务中最多减少35.76%缓存缺失，在在线装箱问题中最多减少30.93%箱子使用。
原文摘要 · Abstract (English)
Designing system algorithms remains challenging, where the discontinuous nature of the solution space often forces system engineers to rely on generic heuristics at the expense of performance. We study whether LLMs can practically drive algorithm generation, and find that they are biased towards well-known generic designs, rather than making the creative leaps needed to navigate the discontinuous solution space. To address this limitation, we introduce MetaMuse, a framework for creative ideation built on three self-reflection principles: (1) quantifying solution diversity and usefulness in measurable performance space, rather than abstract idea space, (2) steering ideation through external stimuli, rather than internal randomness, and (3) constructing executable solutions using waypoint reasoning, rather than free-form chain-of-thought. Considering two critical online problems at a global cloud provider, extensive evaluations show that MetaMuse can generate high-performing solutions: it reduces cache misses by up to 35.76% in cache replacement and reduces bin usage by up to 30.93% in online bin packing.
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。