SIMA 2: A Generalist Embodied Agent for Virtual Worlds
By: SIMA team , Adrian Bolton , Alexander Lerchner and more
Potential Business Impact:
Lets robots learn new skills by playing games.
We introduce SIMA 2, a generalist embodied agent that understands and acts in a wide variety of 3D virtual worlds. Built upon a Gemini foundation model, SIMA 2 represents a significant step toward active, goal-directed interaction within an embodied environment. Unlike prior work (e.g., SIMA 1) limited to simple language commands, SIMA 2 acts as an interactive partner, capable of reasoning about high-level goals, conversing with the user, and handling complex instructions given through language and images. Across a diverse portfolio of games, SIMA 2 substantially closes the gap with human performance and demonstrates robust generalization to previously unseen environments, all while retaining the base model's core reasoning capabilities. Furthermore, we demonstrate a capacity for open-ended self-improvement: by leveraging Gemini to generate tasks and provide rewards, SIMA 2 can autonomously learn new skills from scratch in a new environment. This work validates a path toward creating versatile and continuously learning agents for both virtual and, eventually, physical worlds.
Similar Papers
SimWorld: An Open-ended Realistic Simulator for Autonomous Agents in Physical and Social Worlds
Artificial Intelligence
Lets AI agents learn to live and work in the real world.
Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
Computation and Language
AI learns to imagine futures to solve complex tasks.
Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
Artificial Intelligence
Helps computers do many tasks on their own.