外观
论文arXiv 2610.2231913 天前
一队 Gemini 4 Argon 智能体通关 Minecraft
原文链接：A team of Gemini 4 Argon agents beats Minecraft（arXiv 2610.22319 · 发布日期：2026-10-15）
A team of Gemini 4 Argon agents beats Minecraft
四个 Gemini 4 Argon 智能体通过 Mineflayer 自主协作，在沙盒 Minecraft 生存世界击败末影龙。
核心要点
- 动机是检验 AI 智能体能否完成需长期规划与多智能体协作的 Minecraft 通关。
- 四个智能体经 Mineflayer 控制玩家，用游戏内聊天和共享记忆协调，自行编写调试程序。
- 随机生成世界 Easy 难度下，团队写出 2,783 个程序，27小时14分钟后击败末影龙。
- 研究者可通过仪表盘观察并暂停或停止；论文也描述团队策略和结果局限。
验证范围与局限：验证范围为沙盒 Minecraft 生存世界的一次 Easy 难度随机世界运行。
英文摘要 (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.
作者：Maxence Faldor, Satinder Singh, Roberta Răileanu
来源
本页事实对应的公开页面，以原文为准。