Research

Paper

AI LLM March 05, 2026

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

Authors

Kenan Li, Rongzhi Li, Linghao Zhang, Qirui Jin, Liao Zhu, Xiaosong Huang, Geng Zhang, Yikai Zhang, Shilin He, Chengxing Xie, Xin Zhang, Zijian Jin, Bowen Li, Chaoyun Zhang, Yu Kang, Yufan Huang, Elsie Nallipogu, Saravan Rajmohan, Qingwei Lin, Dongmei Zhang

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.

Metadata

arXiv ID: 2603.05026
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-03-05
Fetched: 2026-03-06 14:20

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.05026v1</id>\n    <title>RepoLaunch: Automating Build&amp;Test Pipeline of Code Repositories on ANY Language and ANY Platform</title>\n    <updated>2026-03-05T10:15:13Z</updated>\n    <link href='https://arxiv.org/abs/2603.05026v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.05026v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-03-05T10:15:13Z</published>\n    <arxiv:comment>Under peer review. 16 pages, 4 figures, 5 tables</arxiv:comment>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Kenan Li</name>\n    </author>\n    <author>\n      <name>Rongzhi Li</name>\n    </author>\n    <author>\n      <name>Linghao Zhang</name>\n    </author>\n    <author>\n      <name>Qirui Jin</name>\n    </author>\n    <author>\n      <name>Liao Zhu</name>\n    </author>\n    <author>\n      <name>Xiaosong Huang</name>\n    </author>\n    <author>\n      <name>Geng Zhang</name>\n    </author>\n    <author>\n      <name>Yikai Zhang</name>\n    </author>\n    <author>\n      <name>Shilin He</name>\n    </author>\n    <author>\n      <name>Chengxing Xie</name>\n    </author>\n    <author>\n      <name>Xin Zhang</name>\n    </author>\n    <author>\n      <name>Zijian Jin</name>\n    </author>\n    <author>\n      <name>Bowen Li</name>\n    </author>\n    <author>\n      <name>Chaoyun Zhang</name>\n    </author>\n    <author>\n      <name>Yu Kang</name>\n    </author>\n    <author>\n      <name>Yufan Huang</name>\n    </author>\n    <author>\n      <name>Elsie Nallipogu</name>\n    </author>\n    <author>\n      <name>Saravan Rajmohan</name>\n    </author>\n    <author>\n      <name>Qingwei Lin</name>\n    </author>\n    <author>\n      <name>Dongmei Zhang</name>\n    </author>\n  </entry>"
}