# CXXCrafter: An LLM-Based Agent for Automated C/C++ Open Source Software Building

arXiv: https://arxiv.org/abs/2505.21069 · HTML: https://mlsanity.com/paper/2505.21069/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 54 references that are in the map.
- First posted on arXiv 27 May 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 16 of 16)

- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge](https://mlsanity.com/paper/1811.00937/) (2018)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions](https://mlsanity.com/paper/2404.13208/) (2024)
- [InferFix: End-to-End Program Repair with LLMs](https://mlsanity.com/paper/2303.07263/) (2023)
- [Large Language Models are In-Context Semantic Reasoners rather than Symbolic Reasoners](https://mlsanity.com/paper/2305.14825/) (2023)
- [Large Language Models for Code Analysis: Do LLMs Really Do Their Job?](https://mlsanity.com/paper/2310.12357/) (2023)
- [DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems](https://mlsanity.com/paper/2407.10701/) (2024)
- [UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging](https://mlsanity.com/paper/2404.17153/) (2024)
- [Exploring Autonomous Agents through the Lens of Large Language Models: A Review](https://mlsanity.com/paper/2404.04442/) (2024)
- [DockerizeMe: Automatic Inference of Environment Dependencies for Python Code Snippets](https://mlsanity.com/paper/1905.11127/) (2019)
- [Automatically Generating Dockerfiles via Deep Learning: Challenges and Promises](https://mlsanity.com/paper/2303.15990/) (2023)
- [Sketch: A Toolkit for Streamlining LLM Operations](https://mlsanity.com/paper/2409.03346/) (2024)
- [Towards Understanding Third-party Library Dependency in C/C++ Ecosystem](https://mlsanity.com/paper/2209.02575/) (2022)
- [Untangling Knots: Leveraging LLM for Error Resolution in Computational Notebooks](https://mlsanity.com/paper/2405.01559/) (2024)
- [CENTRIS: A Precise and Scalable Approach for Identifying Modified Open-Source Software Reuse](https://mlsanity.com/paper/2102.06182/) (2021)

## Built on by (most cited first, 10 of 10)

- [SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks](https://mlsanity.com/paper/2506.10954/) (2025)
- [90% Faster, 100% Code-Free: MLLM-Driven Zero-Code 3D Game Development](https://mlsanity.com/paper/2509.26161/) (2025)
- [RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms](https://mlsanity.com/paper/2603.05026/) (2026)
- [ASEval: Automated Trajectory-Level Security Testing for Autonomous Agents](https://mlsanity.com/paper/2605.22321/) (2026)
- [LLMs as Packagers of HPC Software](https://mlsanity.com/paper/2511.05626/) (2025)
- [DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents](https://mlsanity.com/paper/2511.20709/) (2025)
- [Reproducible, Explainable, and Effective Evaluations of Agentic AI for Software Engineering](https://mlsanity.com/paper/2604.01437/) (2026)
- [Agent-Based Software Artifact Evaluation](https://mlsanity.com/paper/2602.02235/) (2026)
- [Still Manual? Automated Linter Configuration via DSL-Based LLM Compilation of Coding Standards](https://mlsanity.com/paper/2602.07783/) (2026)
- [BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge](https://mlsanity.com/paper/2605.15815/) (2026)

## Abstract (arXiv)

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 capabilities and address complex errors by leveraging tacit knowledge storage. Moreover, LLM-based agents can be systematically designed to dynamically interact with the environment, effectively managing dynamic building issues. Motivated by these opportunities, we first conduct an empirical study to systematically analyze the current challenges in the C/C++ project building process. Particularly, we observe that most popular C/C++ projects encounter an average of five errors when relying solely on the default build systems. Based on our study, we develop an automated build system called CXXCrafter to specifically address the above-mentioned challenges, such as dependency resolution. Our evaluation on open-source software demonstrates that CXXCrafter achieves a success rate of 78% in project building. Specifically, among the Top100 dataset, 72 projects are built successfully by both CXXCrafter and manual efforts, 3 by CXXCrafter only, and 14 manually only. ...