Returning to Development States: When Full Sandbox Snapshots Help Coding Agents

The paper investigates whether restoring full sandbox snapshots can aid coding agents in recovering from failures. By implementing a Go‑Explore‑style search over complete Daytona snapshots, the authors find that higher and more efficient solve rates arise when progress is stored outside the repository—such as in databases, services, and other runtime state. The study suggests that full‑snapshot search is most beneficial for long‑horizon coding tasks that span multiple services whose state cannot be reconstructed from a simple diff.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

• agents