用AI自动复现Minecraft崩溃漏洞，准确率达34.9%
Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft
- 通过大模型将崩溃报告转为可执行操作步骤
- 在真实游戏环境中执行步骤，成功复现34.9%的崩溃
- 适合游戏测试、自动化调试与开发人员使用
复现游戏漏洞，尤其是Minecraft这类持续演进的游戏中的崩溃漏洞，长期依赖人工、耗时且难以自动化；我们对Minecraft关键决策者的访谈证实，大量崩溃报告需手动重建场景。尽管大语言模型在其他软件领域已成功用于漏洞复现，但具有复杂交互环境的游戏仍鲜有研究。本文提出BugCraft，一种端到端框架，可直接从用户提交的漏洞报告中自动化复现Minecraft崩溃问题。该框架采用两阶段设计：首先，步骤生成器利用大模型与Minecraft维基知识，将漏洞报告转化为高质量、结构化的复现步骤（S2R）；其次，动作模型基于视觉大模型代理和自定义宏接口，在Minecraft中执行这些步骤以触发崩溃。为支持评估，我们构建了BugCraft-Bench数据集。在该数据集上，采用GPT-4.1的框架实现了34.9%的端到端复现率，比基线计算机使用模型高出37%。结果表明，大模型可在复杂游戏环境中实现崩溃漏洞的自动化复现，为游戏测试与开发开辟新路径。代码已开源：https://bugcraft2025.github.io
原文摘要 · Abstract (English)
Reproducing game bugs, particularly crash bugs in continuously evolving games like Minecraft, is a notoriously manual, time-consuming, and challenging process to automate; insights from a key decision maker from Minecraft we interviewed confirm this, highlighting that a substantial portion of crash reports necessitate manual scenario reconstruction. Despite the success of LLM-driven bug reproduction in other software domains, games, with their complex interactive environments, remain largely unaddressed. This paper introduces BugCraft, a novel end-to-end framework designed to automate the reproduction of crash bugs in Minecraft directly from user-submitted bug reports, addressing the critical gap in automated game bug reproduction. BugCraft employs a two-stage approach: first, a Step Synthesizer leverages LLMs and Minecraft Wiki knowledge to transform bug reports into high-quality, structured steps to reproduce (S2R). Second, an Action Model, powered by a vision-based LLM agent and a custom macro API, executes these S2R steps within Minecraft to trigger the reported crash. To facilitate evaluation, we introduce BugCraft-Bench, a curated dataset of Minecraft crash bug reports. On BugCraft-Bench, our framework end-to-end reproduced 34.9% of crash bugs with GPT-4.1, outperforming baseline computer-use models by 37%. BugCraft demonstrates the feasibility of automated reproduction of crash bugs in complex game environments using LLMs, opening promising avenues for game testing and development. Finally, we make our code open at https://bugcraft2025.github.io
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。