cs.AINov 17, 2026

Readie: Low-Latency Code Sandboxes for AI Agents

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

Organizations: University of Illinois Urbana-Champaign · ByteDance · Columbia University

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.

Figures & tables

Explore similar work

CardsList
  1. The Rollout Infrastructure Tax in Coding-Agent Reinforcement Learning

    Jul 1, 2026Daniel Thi Graviet, Lovre Pesut, Ivan Dagelic +2RL for Code GenerationSoftware Engineering Agents

  2. DeltaBox: Millisecond-Scale Sandbox Checkpoint and Rollback for Stateful AI Agents

    May 21, 2026Yunpeng Dong, Jingkai He, Shiqi Liu +7LLM Agents