MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft

SummaryAI generated

On September 7, 2026, the arXiv cs.CL platform published the paper “MineExplorer: Evaluating Open-World Exploration of MLLM Agents in Minecraft”. This study aims to evaluate the open-world exploration capabilities of multi-modal large language model agents in the Minecraft game environment.

Related eventsRELATED EVENTS

2026-09-07 21:02The `GPT-6 Astra model was released, and OpenAI President Brockman confidently declared, “Welcome to the era of AGI.”
2026-09-08 19:21OpenAI released GPT-6 Astra, marking the arrival of the AGI era, with capabilities for autonomous computer operation and scientific research.
2026-09-08 22:40① Nvidia CEO Jensen Huang posted that OpenAI’s GPT-6 Astra, released last week, was trained using approximately 100,000 NV Link 72 clusters, and he believes that General Artificial Intelligence (AGI) has officially arrived; ② GPT-6 Astra can directly operate computers and software to perform complex tasks such as programming, reaching the most advanced level in multiple fields. OpenAI has announced the beginning of the AGI era.

Key entitiesKEY ENTITIES

MLLMMei-tuan-LongcatMineExplorerMinecraft

Coverage · reports per dayLANGUAGE SPLIT

Entity relations

SignalsSIGNALS

Keyword heat

MineExplorer1
MLLM1
Minecraft1
Mei-tuan-Longcat1

All reports (1)SOURCES

↗

A arXiv cs.CL en 2026-09-07 12:00

Meituan 团队发布 MineExplorer 基准，用于评估多模态大语言模型在 Minecraft 中的开放世界探索能力。该基准通过过滤依赖特定游戏知识的原子任务、构建 ReAct 风格的多跳隐式任务，并利用多智能体合成工作流生成更可靠的测试实例。实验表明，尽管强模型能处理单步任务，但在需协调长轨迹隐藏前置条件的场景下表现急剧下降；且任务难度与完成度正相关，大模型或特定思考模式并未带来一致的性能提升。代码与数据集已开源。