aifollow.news Search
Back Rohan Paul
Rohan Paul· @rohanpaul_ai · X· · Original publication time AI score54

Google DeepMind paper reports four general-purpose coding agents beat Minecraft without human helpMachine translation

Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.

AI introduction

The paper describes four Gemini 4 Argon agents given only a goal to defeat the Ender Dragon and a standard library that turns JavaScript into game actions. They organized through chat and shared notes, then succeeded in a random world on Easy difficulty after 27 hours and 14 minutes and 2,783 programs. This was a single run, so the setup’s success rate remains unknown.

Original post · Original

The article text is unavailable in this language; an existing version is shown.

@rohanpaul_ai

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.

Source: Rohan Paul · x.com

Research
Found an error? Send a correction