arXiv：cs.AI· Yuxuan Cao, Junlong Li, Hao Li, Junxian He·· 3 小时前
Mine Odyssey：在开放世界中评测智能体空间智能
Mine Odyssey: Benchmarking Spatial Agentic Intelligence in the Wild
AI 导读
研究者推出 Mine Odyssey 基准，用 Minecraft 重建 30 个真实地点，覆盖 5 大洲 20 个国家和地区的 180 项任务，评估智能体的空间智能。GPT-6 Astra 成功率最高达 85.6%，Claude Opus 5.5 为 73.9%，最强开源权重模型 DeepSeek-V4.1-Flash 仅 23.9%，显示当前模型在智能体空间智能上仍有较大提升空间。
正文
Abstract:Advances in foundation models are driving efforts to introduce agents to assist people in the physical world. Such agents require agentic spatial intelligence: exploring unfamiliar environments, updating spatial understanding through interaction, and adapting actions based on feedback to sustain progress toward a sequence of goals. Existing benchmarks cover only a limited range of spatial layouts, scales, and traversal requirements. We introduce Mine Odyssey, a benchmark for evaluating agentic spatial intelligence using Minecraft reconstructions of real-world locations. It comprises 180 tasks covering 30 such locations across 20 countries and regions on five continents, including 20 outdoor and 10 indoor settings. These settings span diverse spatial scales, layouts, terrains, and connectivity patterns, from Midtown Manhattan and rural Entrup to Santa Lucía Hill and Buckingham Palace. We select meaningful waypoints, such as landmarks, buildings, and rooms, and manually verify their accessibility. Each task provides a natural-language instruction specifying which waypoints to visit and in what order. Completing these tasks requires agents to find accessible routes and entrances, open doors, and move between levels using stairs and ladders, while monitoring their progress and recovering from navigation errors. Across eight evaluated state-of-the-art models, GPT-6 Astra achieves the highest success rate of 85.6%. However, the second-best model, Claude Opus 5.5, completes 73.9% of tasks, while the strongest evaluated open-weight model, DeepSeek-V4.1-Flash, reaches 23.9%, highlighting substantial room for improvement in the agentic spatial intelligence of current models. Comprehensive analyses and ablation studies on Mine Odyssey reveal current models' limitations and provide insights for advancing agentic spatial intelligence.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.11328 [cs.AI] |
| (or arXiv:2610.11328v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11328 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuxuan Cao [view email]
[v1]
Thu, 8 Oct 2026 06:26:43 UTC (21,038 KB)
来源：arXiv：cs.AI · arxiv.org