RepoLaunch: Automating Build&Test Pipeline of Code Repositories on ANY Language and ANY Platform

TL;DR

RepoLaunch is an innovative LLM-powered agent that automates dependency resolution, compilation, and testing across diverse programming languages and platforms, significantly streamlining software engineering workflows and dataset creation.

Contribution

It is the first agent capable of fully automating build and test processes for any language and platform, enabling scalable benchmarking and training of coding agents.

Findings

Automates dependency resolution, compilation, and testing across languages and platforms.

Facilitates automated creation of SWE datasets with minimal human intervention.

Supports scalable benchmarking and training of coding agents and LLMs.

Abstract

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.