跳到正文
DEV Community· ToolPilot Pro·· 2026-10-20AI 評分55

4 個 Gemini 4 Argon 智能體在 27 小時 14 分鐘內擊敗《Minecraft》末影龍

4 Gemini 4 Argon Agents Beat Minecraft in 27 Hours, No Humans

AI 導讀

Google DeepMind 的 4 個 Gemini 4 Argon 智能體在隨機《Minecraft》生存世界中歷時 27 小時 14 分鐘擊敗末影龍。它們沒有預設角色或策略,自行形成分工,編寫 2,783 個 JavaScript 程式、交換 229 則聊天訊息並死亡 605 次;第五個 Observer 智能體審核了整場過程。

正文

ToolPilot Pro

Google DeepMind just dropped four Gemini 4 Argon agents into a random Minecraft survival world. No assigned roles. No strategies. No game-specific tools beyond the standard Mineflayer library. Then they watched.

27 hours and 14 minutes later, the Ender Dragon was dead.

Along the way the four agents wrote 2,783 JavaScript programs, swapped 229 chat messages, died 605 times, and organized themselves into emergent roles (one even handled cleanup duty). A fifth "Observer" agent audited the run. Total input: 1.35 billion tokens. Cost at Argon's standard pricing: about $1,620 for the full session.

Why it matters: nobody trained these models to play Minecraft. They reasoned through crafting recipes, split mining and building duties, warned each other about threats, and recovered gear from fallen teammates, all through text and code. That loop — plan, code, fail, revise — is exactly what agentic AI is supposed to do in software development and robotics, not just games.

The honest caveats: it was one run on easy difficulty, Argon already "knows" Minecraft from training data, and a repeat rate is unknown.

Full breakdown, cost math and FAQs: https://toolpilotpro.com/gemini-4-argon-agents-beat-minecraft

來源:DEV Community · dev.to