CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Li, Chen, Guoqiang, Shang, Xiuwei, Cheng, Shaoyin, Wu, Benlong, Li, Gangyang, Zhu, Xu, Zhang, Weiming, Yu, Nenghai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908352750026752
author Hu, Li
Chen, Guoqiang
Shang, Xiuwei
Cheng, Shaoyin
Wu, Benlong
Li, Gangyang
Zhu, Xu
Zhang, Weiming
Yu, Nenghai
author_facet Hu, Li
Chen, Guoqiang
Shang, Xiuwei
Cheng, Shaoyin
Wu, Benlong
Li, Gangyang
Zhu, Xu
Zhang, Weiming
Yu, Nenghai
contents With open-source projects growing in size and complexity, manual compilation becomes tedious and error-prone, highlighting the need for automation to improve efficiency and accuracy. However, the complexity of compilation instruction search and error resolution makes automatic compilation challenging. Inspired by the success of LLM-based agents in various fields, we propose CompileAgent, the first LLM-based agent framework dedicated to repo-level compilation. CompileAgent integrates five tools and a flow-based agent strategy, enabling interaction with software artifacts for compilation instruction search and error resolution. To measure the effectiveness of our method, we design a public repo-level benchmark CompileAgentBench, and we also design two baselines for comparison by combining two compilation-friendly schemes. The performance on this benchmark shows that our method significantly improves the compilation success rate, ranging from 10% to 71%. Meanwhile, we evaluate the performance of CompileAgent under different agent strategies and verify the effectiveness of the flow-based strategy. Additionally, we emphasize the scalability of CompileAgent, further expanding its application prospects.
format Preprint
id arxiv_https___arxiv_org_abs_2505_04254
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System
Hu, Li
Chen, Guoqiang
Shang, Xiuwei
Cheng, Shaoyin
Wu, Benlong
Li, Gangyang
Zhu, Xu
Zhang, Weiming
Yu, Nenghai
Software Engineering
With open-source projects growing in size and complexity, manual compilation becomes tedious and error-prone, highlighting the need for automation to improve efficiency and accuracy. However, the complexity of compilation instruction search and error resolution makes automatic compilation challenging. Inspired by the success of LLM-based agents in various fields, we propose CompileAgent, the first LLM-based agent framework dedicated to repo-level compilation. CompileAgent integrates five tools and a flow-based agent strategy, enabling interaction with software artifacts for compilation instruction search and error resolution. To measure the effectiveness of our method, we design a public repo-level benchmark CompileAgentBench, and we also design two baselines for comparison by combining two compilation-friendly schemes. The performance on this benchmark shows that our method significantly improves the compilation success rate, ranging from 10% to 71%. Meanwhile, we evaluate the performance of CompileAgent under different agent strategies and verify the effectiveness of the flow-based strategy. Additionally, we emphasize the scalability of CompileAgent, further expanding its application prospects.
title CompileAgent: Automated Real-World Repo-Level Compilation with Tool-Integrated LLM-based Agent System
topic Software Engineering
url https://arxiv.org/abs/2505.04254