arXiv cs.AI· Arjun Sivaraman, Zhaoheng Li, Alan Shi, Sanjay Malisetty, Eugene Wu, Yongjoo Park·· 4 小时前AI 评分34
Readie:面向 AI 智能体的低延迟代码沙箱
Readie: Low-Latency Code Sandboxes for AI Agents
AI 导读
Readie 通过“学习式启动快照”为 AI 智能体降低代码沙箱启动延迟,在同等存储预算下将启动延迟降低 3-22 倍、端到端运行时间缩短 1.3-3.3 倍。该方法从大规模训练负载中学习一组小型快照,每个快照初始化快且覆盖部分智能体生成代码,合起来覆盖大部分工作负载,并在 15K 公开及 LLM 合成脚本上完成规划验证。
正文 · 原文
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 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Arjun Sivaraman [view email]
[v1]
Tue, 17 Nov 2026 04:04:11 UTC (91 KB)
来源:arXiv cs.AI · arxiv.org