





















Authors:Shu Liu, Alexander Krentsel, Shubham Agarwal, Mert Cemri, Ziming Mao, Soujanya Ponnapalli, Alexandros G. Dimakis, Sylvia Ratnasamy, Matei Zaharia, Aditya Parameswaran, Ion Stoica
Abstract: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.
| Comments: | preprint |
| Subjects: | Databases (cs.DB); Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Software Engineering (cs.SE) |
| Cite as: | arXiv:2605.24096 [cs.DB] |
| (or arXiv:2605.24096v1 [cs.DB] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24096 arXiv-issued DOI via DataCite (pending registration) |
From: Shu Liu [view email]
[v1]
Fri, 22 May 2026 18:03:41 UTC (867 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。