DeepMind Paper: Four General Coding Agents Autonomously Beat Minecraft
A new Google DeepMind paper demonstrates that four general-purpose coding agents based on Gemini 4 Argon successfully beat Minecraft without human intervention. The agents autonomously organized via chat and shared memory, writing thousands of programs to coordinate long-horizon dependent tasks, proving the capability of generic code agents in complex planning.
Full Report
Rohan Paul (@rohanpaul_ai) · 2026-10-26 21
New Google DeepMind paper shows 4 general-purpose coding agents beating Minecraft with no human help, writing every program and splitting the work themselves.
Finishing Minecraft means holding 1 plan across thousands of dependent steps, the same skill long software and business tasks need. Earlier Minecraft agents were trained on gameplay or handed game-specific planners.
Each Gemini 4 Argon agent got 1 goal, defeat the Ender Dragon, and a standard library that turns JavaScript into game actions. Nobody assigned roles or wrote game tools, so the team organized itself through chat and shared notes.
From a random world on Easy difficulty, they killed the dragon in 27 hours and 14 minutes, writing 2,783 programs and dying 605 times. It was a single run, so how often this setup succeeds is still unknown.
Before writing custom planners for a long task, try general coding agents with a plain API and a shared memory.
