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

2026-03-05

AI Summary

This work proposes RepoLaunch, the first fully automated agent capable of cross-language and cross-platform software repository building and testing. Addressing the heavy reliance on manual intervention in existing workflows under heterogeneous environments, RepoLaunch leverages a large language model to integrate dependency resolution, compilation execution, and test result extraction. Given only a task specification, it autonomously generates high-quality datasets for training and evaluating Software Engineering (SWE) models. The approach substantially improves both the efficiency and coverage of dataset construction and has already enabled automatic task generation and benchmark evaluation in multiple cutting-edge research efforts.

Technology Category

Natural Language Processing: Code Generation / Program Synthesis from Natural LanguageMachine Learning: Large Multimodal Models (LMMs)Planning, Routing, and Scheduling: Planning with Language Models

Application Category

Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web searchEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systemsSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• build automation
• test pipeline
• code repositories
• software engineering
• cross-platform

Innovation

• LLM agents
• cross-language automation
• build-and-test pipeline
• automated dataset generation
• software engineering automation