RepoLaunch: Automating Build&Test Pipeline of Code Repositories on ANY Language and ANY Platform
This work addresses the problem of manual effort in building and testing software repositories for developers and researchers, enabling scalable benchmarking and training of coding agents and LLMs.
RepoLaunch is an LLM agent that automates the build and test pipeline for software repositories, handling dependency resolution, compilation, and test result extraction across various languages and platforms. It enables a fully automated pipeline for creating SWE datasets, with human intervention only for task design.
Building software repositories typically requires significant manual effort. Recent advances in large language model (LLM) agents have accelerated automation in software engineering (SWE). We introduce RepoLaunch, the first agent capable of automatically resolving dependencies, compiling source code, and extracting test results for repositories across arbitrary programming languages and operating systems. To demonstrate its utility, we further propose a fully automated pipeline for SWE dataset creation, where task design is the only human intervention. RepoLaunch automates the remaining steps, enabling scalable benchmarking and training of coding agents and LLMs. Notably, several works on agentic benchmarking and training have recently adopted RepoLaunch for automated task generation.