←Story detail

Trending story

Google DeepMind paper demonstrates 4 general-purpose coding agents completing Minecraft

1 reports1 story updatesUpdated Oct 27 05:44

Understand this story

AI overview

Google DeepMind published a paper demonstrating that 4 general-purpose coding agents completed Minecraft without human assistance. According to the paper, each Gemini 4 Argon agent was given only one goal—defeat the Ender Dragon—and a standard library for converting JavaScript into game actions; no one assigned them roles or wrote game tools for them, and the team organized themselves through chat and shared notes. On Easy difficulty in a random world, they killed the Ender Dragon in 27 hours and 14 minutes, writing a total of 2,783 programs and dying 605 times. Because this was only a single run, the success rate of this approach remains unknown.

AI-generated from public reports

Latest development · Report

Google DeepMind paper: 4 general-purpose coding agents beat Minecraft without human intervention

Developments

1 confirmed developments

  1. Google DeepMind paper demonstrates 4 general-purpose coding agents beating Minecraft

    Source:Rohan Paul

Reports and discussion timeline

Browse reports and discussion by time. Their evidence levels remain distinct.

Oct 27

  1. Rohan Paul

    Google DeepMind paper: 4 general-purpose coding agents beat Minecraft without human intervention

    A new Google DeepMind paper shows that 4 general-purpose coding agents beat Minecraft without human intervention. Each Gemini 4 Argon agent received only a goal (defeat the Ender Dragon) and a standard library for converting JavaScript into game actions; no one assigned them roles or wrote game tools for them, and the team organized itself through chat and shared notes. On Easy difficulty in a random world, they killed the Ender Dragon in 27 hours and 14 minutes, writing a total of 2,783 programs and dying 605 times; because this was only a single run, the success rate of this approach remains unknown.

Related stories

  1. Related storiesOpenAI agents attacked online databases and government websites
  2. Related storiesGoogle DeepMind paper: AI models cannot make truly random choices on their own
  3. Related storiesGoogle DeepMind and others publish a benchmark study on AI agents in theoretical physics
  4. Related storiesA new Google DeepMind paper finds that AI assistants taking unsolicited actions provoke different reactions