CXXCrafter: An LLM-Based Agent for Automated C/C++ Open Source Software Building
Zhengmin Yu, Yuan Zhang, Ming Wen, Yinan Nie, Wenhui Zhang, Min Yang

TL;DR
This paper introduces CXXCrafter, an LLM-based agent designed to automate the complex process of building C/C++ open source projects, addressing dependency management and error handling to improve success rates.
Contribution
It presents the first systematic analysis of C/C++ build challenges and develops an LLM-powered system that automates project building with a 78% success rate on open-source projects.
Findings
Most C/C++ projects encounter around five build errors with default systems.
CXXCrafter successfully builds 78% of projects in the evaluation.
The system outperforms manual building in certain cases.
Abstract
Project building is pivotal to support various program analysis tasks, such as generating intermediate rep- resentation code for static analysis and preparing binary code for vulnerability reproduction. However, automating the building process for C/C++ projects is a highly complex endeavor, involving tremendous technical challenges, such as intricate dependency management, diverse build systems, varied toolchains, and multifaceted error handling mechanisms. Consequently, building C/C++ projects often proves to be difficult in practice, hindering the progress of downstream applications. Unfortunately, research on facilitating the building of C/C++ projects remains to be inadequate. The emergence of Large Language Models (LLMs) offers promising solutions to automated software building. Trained on extensive corpora, LLMs can help unify diverse build systems through their comprehension…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
