跳到正文

Readie: Low-Latency Code Sandboxes for AI Agents

大数据 0 次浏览

原文:Readie: Low-Latency Code Sandboxes for AI Agents

作者:Arjun Sivaraman, Zhaoheng Li, Alan Shi, Sanjay Malisetty, Eugene Wu, Yongjoo Park

来源:arXiv cs.DB(数据库)

正文

Computer Science > Artificial Intelligence

arXiv:2611.22171v1 (cs)

[Submitted on 17 Nov 2026]

Title:Readie: Low-Latency Code Sandboxes for AI Agents

Authors:Arjun Sivaraman, Zhaoheng Li, Alan Shi, Sanjay Malisetty, Eugene Wu, Yongjoo Park

View a PDF of the paper titled Readie: Low-Latency Code Sandboxes for AI Agents, by Arjun Sivaraman and 5 other authors

View PDF

HTML (experimental)

Abstract:From quantitative research to personal assistance, AI agents act by iteratively generating and executing code. To decouple the agent harness from code execution, many agents offload execution to dedicated systems called code sandboxes. However, existing code sandboxes suffer from slow startup. Whether they rely on custom snapshots or a single fat image, the root cause is the same: it is hard to build a compact, pre-warmed snapshot that can be shared across diverse agent-generated code while covering nearly all the artifacts (e.g., packages, datasets) it requires.

In this work, we propose learned startup snapshots for low-latency code sandboxes. Our insight is that while it is hard for a single snapshot to be both compact and cover most workloads, a set of snapshots can achieve both. Each snapshot is small, initializes quickly, and covers a fraction of agent-generated code; together, the set covers most of it. We learn this set from a large training workload by formulating snapshot construction as an optimization problem and solving it with an approximation algorithm. Planned on 15K public and LLM-synthesized scripts, our system, Readie, reduces startup latency by 3-22$\times$ and end-to-end runtime by 1.3-3.3$\times$ compared to existing approaches at the same storage budget.

Subjects:

Artificial Intelligence (cs.AI); Databases (cs.DB); Software Engineering (cs.SE)

Cite as:

arXiv:2611.22171 [cs.AI]

(or

arXiv:2611.22171v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2611.22171

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

人工智能 · 数据库 · 软件工程


由「前沿雷达」于 2026-11-17 采集。正文取自原文页面,已保留出处链接。标题与正文版权归原作者所有。

评论

加载中…