Readie:面向 AI Agent 的低延迟代码沙箱快照方案
Readie: Low-Latency Code Sandboxes for AI Agents
做 Agent 开发的都会遇到沙箱冷启动拖慢执行的问题。这篇论文用一组学习出来的小快照替代单个大快照,启动延迟降 3-22 倍,思路挺巧的,论文来自 arXiv,感兴趣可以直接看实现细节。
Readie 是一项针对代码沙箱启动慢问题的研究,提出“学习型启动快照”:用一组快照代替单一快照来覆盖多样化的 agent 生成代码。核心洞察是单个快照难以同时做到紧凑和高覆盖率,而多个小快照各自快速初始化、各覆盖一部分代码,集合起来即可覆盖绝大多数工作负载。团队将快照构建形式化为优化问题,用近似算法从大规模训练工作负载中求解。
在 15K 条公开与 LLM 合成脚本上的规划显示,Readie 在相同存储预算下将启动延迟降低 3-22 倍,端到端运行时间降低 1.3-3.3 倍。对依赖迭代生成并执行代码的 agent(量化研究、个人助理等场景),这能显著缩短任务响应时间,是沙箱基础设施层面的优化。
Readie: Low-Latency Code Sandboxes for AI Agents
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.
本条情报归属 AITOP「论文」核心栏目,重点聚焦北美前沿实验室与硅谷科技巨头。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Readie、代码沙箱、智能体、代码执行,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Arjun Sivaraman, Zhaoheng Li, Alan Shi, Sanjay Malisetty, Eugene Wu, Yongjoo Park),经 AITOP 多维评分管线结构化提炼。