Returning to Development States: When Full Sandbox Snapshots Help Coding Agents
Daniel Thi Graviet, Tanmay Shah
Abstract
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.
Create a lesson
Related papers
To Defer or Not to Defer? Online Learning with LLMs and Congested Experts
Vasileios Saketos, William Reveillard, Alexandre Proutiere et al.
ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer
Can Jin, Yan Kang, Yifan Gong et al.
scHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data
Ugo Lomoio, Pietro Hiram Guzzi, Pierangelo Veltri
RELAGRAM: Recursive Latent Graph Model for the Capacitated Vehicle Routing Problem
Vladimir Kirill Bickov, Neil Yorke-Smith
Random Feature Pruning for Multi-Class Classification
Mohammad Amin Omidi, Babak Seyfe, Shahrokh Valaee
Anchors Enhance Controllability and Reasoning of Diffusion Language Models
Feiyu Qu, Zheng Huang, Andrea Zanette