DockSmith: Scaling Reliable Coding Environments via an Agentic Docker Builder

TL;DR

DockSmith is an agentic Docker builder that enhances environment construction for software engineering tasks by exercising long-horizon reasoning, dependency management, and failure recovery, leading to state-of-the-art performance.

Contribution

Introducing DockSmith, a novel agentic Docker builder trained on large-scale trajectories, enabling scalable, reliable environment construction with broader agentic benefits.

Findings

Achieves 39.72% Fail-to-Pass on Multi-Docker-Eval

Reaches 58.28% Commit Rate on Docker tasks

Improves out-of-distribution performance on multiple benchmarks

Abstract

Reliable Docker-based environment construction is a dominant bottleneck for scaling execution-grounded training and evaluation of software engineering agents. We introduce DockSmith, a specialized agentic Docker builder designed to address this challenge. DockSmith treats environment construction not only as a preprocessing step, but as a core agentic capability that exercises long-horizon tool use, dependency reasoning, and failure recovery, yielding supervision that transfers beyond Docker building itself. DockSmith is trained on large-scale, execution-grounded Docker-building trajectories produced by a SWE-Factory-style pipeline augmented with a loop-detection controller and a cross-task success memory. Training a 30B-A3B model on these trajectories achieves open-source state-of-the-art performance on Multi-Docker-Eval, with 39.72% Fail-to-Pass and 58.28% Commit Rate. Moreover, DockSmith improves out-of-distribution performance on SWE-bench Verified, SWE-bench Multilingual, and Terminal-Bench 2.0, demonstrating broader agentic benefits of environment construction.