Gemini 4 agents autonomously beat Minecraft, Google researchers say

In the experiment, the team placed four AI agents in a sandboxed, randomized Minecraft survival world with the goal of defeating the Ender Dragon. No roles, strategies or game-specific tools were assigned. Each agent controlled a player through the open-source Mineflayer library and coordinated with teammates through in-game chat and shared memory.

The agents quickly chose to split up tasks. They warned one another about threats, offered lessons and tips, shared coordinates and recovered items from dead teammates. Each settled into a role: 'janesick' made tools, 'gyldenia' gathered food and supplies, 'auratian' lit a key portal, and 'bulicame' built Enderman shelters and landed the final blow.

The run took 27.23 hours, with most of that time spent on the Ender Dragon. The team said the four agents wrote and ran 2,783 programs, exchanged 229 messages and died 605 times. A fifth agent called 'the Observer' monitored the session as an independent witness, both to check for cheating and to publish live and summary reports. The agents used 1.35 billion input tokens, and the final cost was $810 at Gemini’s list price or $1,620 at the standard price.

The experiment, Engadget reported, shows how general agentic AI models can now beat complex games, a feat that used to require custom AI software. "To our knowledge, this is the first end-to-end autonomous completion of Minecraft by AI agents, achieved using only the standard Mineflayer library without pre-scouted seeds or other game-specific tools written by humans," the team wrote. "Winning required the agents to keep a coherent plan across thousands of dependent steps for more than a day."