arXiv cs.AI· Maxence Faldor, Satinder Singh, Roberta Raileanu·· 2 天前AI 评分71
四个 Gemini 4 Argon 智能体自主通关 Minecraft
A team of Gemini 4 Argon agents beats Minecraft
AI 导读
研究团队将四个 Gemini 4 Argon 智能体放入沙盒 Minecraft 生存世界，目标是击败末影龙。每个智能体通过开源库 Mineflayer 控制一名玩家，并用游戏内聊天和共享记忆协作，没有人为分配角色或编写游戏逻辑，程序全部由智能体自行规划、编写和调试。
正文 · 原文
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：arXiv cs.AI · arxiv.org