一句话：提出 BugCraft，用 LLM 将 Minecraft 崩溃报告转为复现步骤，并由视觉智能体在游戏内执行，实现端到端自动复现。
在 Minecraft 等持续演化的游戏中，崩溃 bug 复现高度依赖人工场景重建，而已有 LLM 驱动的 bug 复现研究很少覆盖复杂交互式游戏。本文提出 BugCraft：第一阶段 Step Synthesizer 结合 LLM 与 Minecraft Wiki 知识，将崩溃报告转化为结构化的复现步骤（S2R）；第二阶段 Action Model 使用基于视觉的 LLM 智能体和自定义宏 API，在游戏中执行这些步骤以触发崩溃。作者构建 BugCraft-Bench 数据集进行评估，使用 GPT-4.1 端到端复现了 34.9% 的崩溃 bug，比计算机使用基线模型高 37%，表明 LLM 自动复现复杂游戏崩溃 bug 的可行性。
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.
DOI 原文 ·
@inproceedings{paperbot9424,
title = {Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft},
author = {Eray Yapağcı and Yavuz Alp Sencer Öztürk and Eray Tüzün},
booktitle = {ASE},
year = {2025},
doi = {10.1109/ase63991.2025.00254}
}