RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms

arXiv:2603.05026 · cs.SE, cs.LG, cs.MA · Submitted 2026-03-05 · Read on arXiv

cs.SE, cs.LG, cs.MA

Submitted: 2026-03-05

Updated: 2026-10-03

Code: https://github.com/microsoft/RepoLaunch

Project page: https://swe-bench-live.github.io

License: http://creativecommons.org/licenses/by/4.0/

The gist: Language model (LM) agents have driven substantial progress in automated software engineering (SWE), yet building and testing software repositories at scale remains a largely manual and

Terminology

Abstract

Language model (LM) agents have driven substantial progress in automated software engineering (SWE), yet building and testing software repositories at scale remains a largely manual and labor-intensive bottleneck. In this work, we introduce RepoLaunch, a novel agentic framework that automatically resolves dependencies, compiles source code, and extracts test results across diverse programming languages and operating systems. RepoLaunch achieves a 78% build success rate, outperforming the Python/Linux-only prior system by 18%. To demonstrate its application, we further present a fully automated pipeline for SWE dataset creation driven by RepoLaunch, which only requires human input at the task-design stage. RepoLaunch is open-sourced, and its automated task-generation pipeline has been adopted by several recent works on agentic benchmarking and training.

Sources

Related papers