Google DeepMind 发布 Gemini 4 Argon 机器人物理推理模型
原标题：Gemini 4 Argon for Robotics
AI 摘要
Google DeepMind 发布 Gemini 4 Argon，一款面向机器人领域的通用物理推理模型，在 Embodied Reasoning（ERQA）基准上以纯推理取得 87% 成绩，超越其他前沿模型。该模型可覆盖机器人全生命周期，包括控制 Boston Dynamics Spot 四足机器人学习踩踏板扔易拉罐、操控机械臂扶正杯子并放入纸巾、在 Gemini Omni 世界模型中闭环操控拼出 ARGON 字母，以及从真实遥操作数据构建 MuJoCo 数字孪生。
正文节选
Gemini 4 Argon marks a step change in physical understanding, code generation, and visual-semantic reasoning—unlocking new workflows across the robotics stack and accelerating progress toward physical AGI. You can see this leap in capability on the Embodied Reasoning (ERQA) benchmark, which tests a model's ability to understand and solve physical, spatial problems in 3D environments. Using pure reasoning, Argon scores 87%, outperforming every other frontier model. As a general-purpose physical r