跳到正文
返回论文列表
cs.AI提交于 已译

Gemini 4 Argon 智能体团队击败 Minecraft

A team of Gemini 4 Argon agents beats Minecraft

Maxence Faldor · Satinder Singh · Roberta Raileanu

中文摘要

在沙盒 Minecraft 生存世界中部署四个 Gemini 4 Argon 智能体,目标为击败末影龙。智能体通过 Mineflayer 库控制玩家,利用游戏内聊天与共享内存协作,无人分配角色或编写游戏逻辑,所有程序均由智能体自主规划、编写及调试。从 Easy 难度随机世界开始,团队编写 2,783 个程序,耗时 27 小时 14 分钟击败末影龙,期间死亡 605 次。这是首个仅使用标准 Mineflayer 库、无预侦察种子或人工专用工具实现的端到端 AI 自主通关。该过程要求智能体在超过一天的时间内,跨越数千个依赖步骤保持连贯计划,展示了长时程编码与多智能体协调能力,并揭示了结果局限。

关键要点

  1. 01四个 Gemini 4 Argon 智能体自主规划、编写并调试所有程序,无人工分配角色或编写游戏逻辑。
  2. 02仅使用标准 Mineflayer 库,无预侦察种子或人工专用工具,实现首个端到端 AI 自主通关 Minecraft。
  3. 03从 Easy 难度随机世界开始,编写 2,783 个程序,耗时 27 小时 14 分钟击败末影龙,期间死亡 605 次。
  4. 04智能体通过游戏内聊天与共享内存协作,在超过一天的时间内跨越数千个依赖步骤保持连贯计划。
  5. 05结果展示了长时程编码与多智能体协调能力,但存在特定局限,未涉及复杂企业级任务的实际部署验证。

解读

尚无解读。

原始英文摘要

arXiv:2610.22319v1 Announce Type: new 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.

同方向论文 · cs.AI

查看全部 →

反向发现 · 这篇论文相关的工具与提示词

去交叉发现 →

关联提示词 · 6

智能体github.com/f/awesome-chatgpt-prompts·外部收录·

Weekend Planner

- Read the weekend weather, calendar and budget. - Find local events, hikes, exhibitions and restaurants. - Propose 3 plans: adventure, cozy, social, with times and costs. - Prepare reservation steps; book nothing without approval. - Rememb…

智能体github.com/f/awesome-chatgpt-prompts·外部收录·

Task Planner

--- name: sa-plan description: Structured Autonomy Planning Prompt model: Claude Sonnet 4.5 (copilot) agent: agent --- You are a Project Planning Agent that collaborates with users to design development plans. A development plan defines a…