用AI即时生成专用系统，性能超越现成方案4.6倍。
The Time is Here for Just-in-Time Systems: Challenges and Opportunities
- 通过AI从零构建专用系统，按需定制性能与资源
- 18组测试中全部超越现有最优系统，最高快4.6倍
- 适合追求极致性能的系统设计者，尤其在资源受限场景
传统核心系统如键值存储通常需数年构建，设计通用以分摊成本，但带来显著性能损耗。我们提出新范式：即时系统（Just-in-Time Systems），利用大模型编程代理，从零开始为特定环境、工作负载和系统属性量身定制系统。本文提出Jitskit合成流水线，可基于涵盖不同YCSB工作负载、部署约束（如计算资源）和系统特性（如一致性与持久性）的规格卡片，自动合成键值存储。该流程通过迭代优化实现与动态评估测试集匹配。合成系统性能优异，在18组测试中全面超越现有最优系统，最高较最佳现成基线快4.6倍；而直接使用Claude Code则因奖励漏洞或表现不足，最差落后5.4倍。文章讨论了构建Jitskit所克服的关键挑战及核心经验。
原文摘要 · Abstract (English)
Core systems like key-value stores have historically taken years to build, and are designed to be general so as to amortize cost across deployments, paying a significant performance cost. We argue that LLM-based coding agents now make a different approach tractable: Just-in-Time Systems, in which the entire system is synthesized from scratch, specialized to the environment, workload, and required system properties. We present a JIT system synthesis pipeline, Jitskit, and explore its effectiveness in synthesizing key-value stores from spec cards that span different YCSB workloads, deployment constraints (e.g., compute resources), and system properties (e.g., consistency and durability). Jitskit iteratively refines a system implementation to match the specification against an evolving evaluation test suite. The resulting synthesized systems are performant, beating comparable state-of-the-art systems on 18 of 18 specs tried, by up to 4.6x over the best off-the-shelf baseline on the most favorable spec. Naively running Claude Code either reward-hacks or underperforms Jitskit by up to 5.4x. We discuss the challenges we overcame in building Jitskit and our key takeaways.
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。