代码代理开发状态恢复研究
Returning to Development States: When Full Sandbox Snapshots Help Coding Agents
这篇论文解决了代码代理失败后如何有效恢复的问题，通过保存完整开发状态避免了从零开始重试。
研究人员实现了基于Go-Explore风格的完整Daytona快照搜索方法。实验表明，当长时程编程工作涉及多个服务时，完整快照搜索效果最佳。这种技术能显著提高解决效率，尤其适用于无法通过单一diff重建状态的多服务场景。快照中保存的数据库、服务等运行时状态对恢复进度至关重要。
Returning to Development States: When Full Sandbox Snapshots Help Coding Agents
Coding agents often make useful progress before they fail, but retry-from-scratch discards the machine state created along the way. This makes failure recovery an interesting search problem: if intermediate environment states preserve meaningful progress, restoring and branching from them could outperform repeatedly restarting from the initial state. We implement Go-Explore-style search over full Daytona snapshots and find that higher and more efficient solve rates depend mainly on progress that sits outside the repository, such as databases, services, and other runtime state. Our results suggest that full-snapshot search is most effective when long-horizon coding work spans multiple services whose state cannot be reconstructed from a single diff.
