24 August 2026
Google DeepMind trains AI agents in EVE Online game
First reported
AI Breakfast ran this on .
- Google DeepMind set up AI agents in an isolated EVE Online server to test how they learn and plan over long periods.
- The experiment focuses on multi-agent behavior, meaning how AI systems interact with each other in complex shared environments.
- DeepMind plans to expand testing to EVE Frontier, where game rules and economies change over time, presenting new challenges.
How it was covered
AI BreakfastIndependent editors
Google DeepMind is training AI agents in an isolated EVE Online server to test long-term memory, continual learning, planning and multi-agent behavior, with potential expansion to EVE Frontier where agents face changing rules and persistent economies.