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.

翻译：本文介绍了 SIMA 2，一种能够理解并广泛作用于各类三维虚拟世界的通用具身智能体。基于 Gemini 基础模型构建，SIMA 2 代表了在具身环境中实现主动、目标导向交互的重要进展。与先前局限于简单语言指令的工作（例如 SIMA 1）不同，SIMA 2 扮演着交互伙伴的角色，能够推理高层次目标、与用户对话，并处理通过语言和图像给出的复杂指令。在多样化的游戏组合中，SIMA 2 显著缩小了与人类表现的差距，并展现出对先前未见环境的强大泛化能力，同时保留了基础模型的核心推理能力。此外，我们展示了其开放式自我改进的能力：通过利用 Gemini 生成任务并提供奖励，SIMA 2 能够在全新环境中从零开始自主学习新技能。这项工作验证了为虚拟世界乃至最终物理世界创造多功能且持续学习智能体的可行路径。