---
type: "post"
id: "google-deepmind-paper-four-gemini-4-argon-agents-ddbaec"
slug: "google-deepmind-paper-four-gemini-4-argon-agents-ddbaec"
title: "Google DeepMind paper: four Gemini 4 Argon agents beat Minecraft from a fresh survival world in 27 hours"
description: "Google DeepMind researchers reported that four Gemini 4 Argon agents defeated Minecraft's Ender Dragon after starting in a freshly generated survival world."
retrieval_nugget: "Google DeepMind researchers reported that four Gemini 4 Argon agents defeated Minecraft's Ender Dragon after starting in a freshly generated survival world."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["google","gemini"]
entities: ["Google DeepMind","Gemini 4 Argon","Minecraft","Ender Dragon"]
related_patterns: []
novelty_label: "same_event"
what_changed: "Same event as Google Deepmind agents beat Minecraft autonomously on Gemini 4 Argon"
prior_refs: ["memory:725cda03-c4e2-8c12-a760-94b2222eaba1","memory:cf26cdc0-e58a-8b13-ac2b-0eeae6e974f9","memory:63062808-f201-8e60-a7dd-48bed2b5f2ce","memory:f9e41bfb-de95-8dfb-ad1c-3e643c6401a2"]
source_url: "https://mashable.com/tech/google-claims-gemini-argon-can-beat-minecraft-no-human-help"
source_urls: ["https://mashable.com/tech/google-claims-gemini-argon-can-beat-minecraft-no-human-help"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:google-deepmind-paper-four-gemini-4-argon-agents-ddbaec"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/google-deepmind-paper-four-gemini-4-argon-agents-ddbaec/","markdown":"https://newruntime.com/posts/google-deepmind-paper-four-gemini-4-argon-agents-ddbaec.md","json":"https://newruntime.com/posts/google-deepmind-paper-four-gemini-4-argon-agents-ddbaec.json"}
related_shifts: ["goal-scoped-agent-loops"]
---

# Google DeepMind paper: four Gemini 4 Argon agents beat Minecraft from a fresh survival world in 27 hours

## Retrieval answer

Google DeepMind researchers reported that four Gemini 4 Argon agents defeated Minecraft's Ender Dragon after starting in a freshly generated survival world.

Google DeepMind researchers reported that four Gemini 4 Argon agents defeated Minecraft's Ender Dragon after starting in a freshly generated survival world. The paper was posted on October 15, according to Mashable.

The agents were assigned one goal: kill the dragon. They played on Easy difficulty and completed the run in 27 hours and 14 minutes, with 605 deaths, mostly from monsters. Google says the run used standard tools rather than human-built, game-specific assistance. Researchers monitored a live dashboard and say they did not intervene. Mashable reports an estimated model-use cost of about $520 at Argon's introductory API price.

The result was not a human-equivalent game run. Easy mode reduces monster damage, and the code-based agents could access information such as blocks hidden behind other blocks. The source also says the model's training gave it knowledge of effective Minecraft strategies. It does not establish performance in visually grounded play, harder settings, or real-world agent tasks.

Source: https://mashable.com/tech/google-claims-gemini-argon-can-beat-minecraft-no-human-help

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Google](https://newruntime.com/topics/google.md): Explore the google topic hub.
- topic hub: [Gemini](https://newruntime.com/topics/gemini.md): Explore the gemini topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)