HuggingFace Daily Papers·· 2 天前
Gemini 4 Argon 智能体团队自主通关 Minecraft
A team of Gemini 4 Argon agents beats Minecraft
AI 导读
四个 Gemini 4 Argon 智能体在沙盒 Minecraft 生存世界中仅凭一个目标——击败末影龙——自主完成通关。它们通过开源库 Mineflayer 操控玩家，靠游戏内聊天和共享记忆协作，从随机生成的 Easy 难度世界出发，自行编写并调试了 2,783 个程序，在 27 小时 14 分钟内击败末影龙，期间死亡 605 次。研究团队全程仅通过实时仪表盘观察，没有干预。
正文
Abstract:We placed four Gemini 4 Argon agents in a sandboxed Minecraft survival world and gave them one goal: defeat the Ender Dragon. Each agent controlled a player via an open-source library called Mineflayer and coordinated with its teammates through in-game chat and shared memory. No one assigned roles or wrote game logic. The agents planned, wrote, and debugged every program themselves. Researchers could watch the run on a live dashboard and pause or stop it at any time, but they had no cause to intervene. Starting from a randomly generated world on Easy difficulty, the team wrote 2,783 programs and defeated the dragon in 27 hours and 14 minutes, dying 605 times along the way. To our knowledge, this is the first end-to-end autonomous completion of Minecraft by AI agents, achieved using only the standard Mineflayer library without pre-scouted seeds or other game-specific tools written by humans. Winning required the agents to keep a coherent plan across thousands of dependent steps for more than a day. Complex real-world software engineering and enterprise tasks demand the same long-horizon coding and multi-agent coordination. We describe the setup, how the run unfolded, the team's strategies (dividing the work, sharing what they learned, recovering each other's items), and the limits of the result.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.22319 [cs.AI] |
| (or arXiv:2610.22319v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22319 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Maxence Faldor [view email]
[v1]
Thu, 15 Oct 2026 17:51:32 UTC (5,765 KB)
来源：HuggingFace Daily Papers · arxiv.org