Gemini 4 Argon 正式面向所有人开放，加速机器人与物理 AGI 研发
英文标题：🔶 Gemini 4 Argon is now available for everyone
Google 宣布 Gemini 4 Argon 正式面向所有人开放。该模型结合了高级视觉语义推理、深度物理理解与自主代码生成能力，在具身推理基准 ERQA 上以纯推理斩获 87% 的高分，领先所有其他前沿模型。在实测中，Argon 仅通过观看人类投掷沙包的普通视频，便自主生成仿真代码并部署至 Apptronik 的 Apollo 人形机器人，实现了连续 7 次精准命中。这一“视频到仿真再到现实”（Video-to-Sim-to-Real）工作流将原本需耗费数周的手工建模压缩至数小时，为开发者提供了可扩展的机器人训练新范式。
9.8 KB
1.1 MB
中文
加速机器人开发
通过融合先进的视觉语义推理、深度物理理解以及自主代码生成能力，Argon 开辟了贯穿整个机器人技术栈的全新工作流，并加速了迈向物理通用人工智能（Physical AGI）的进程。这一能力的飞跃体现在 Argon 在 具身推理（ERQA）基准测试 中的表现上。该基准专门测试模型在 3D 环境中理解并解决物理与空间问题的能力。完全凭借纯粹的推理能力，Argon 以 87% 的得分超越了所有其他前沿模型。
为了在实践中展示这些能力，我们测试了 Argon 仅通过“观看”来学习分布外物理技能的能力。在一项内部测试中，Argon 观看了人类玩康沃尔沙包（cornhole）的原始视频，映射出环境的空间坐标，并计算了所需的全身关节运动。随后，它自主构建了仿真代码。当这些代码迁移到 Apptronik 的 Apollo 人形机器人上时，该机器人在现实世界的试验中迅速实现了连续 7 次命中。
这种“视频到仿真再到现实”（Video-to-Sim-to-Real）流程将数周的手工仿真建模压缩至数小时，把普通视频转变成机器人技术可扩展的无限训练场。欢迎在 我们的开发者博客 中了解更多关于这如何加速机器人开发步伐的内容。
English / 原文
Speeding up robotics development
By bringing together advanced visual-semantic reasoning, deep physical understanding, and autonomous code generation, Argon unlocks new workflows across the robotics stack and accelerates progress toward physical AGI. This leap in capability is reflected in Argon’s performance on the Embodied Reasoning (ERQA) benchmark, which tests a model's ability to understand and solve physical, spatial problems in 3D environments. Relying on pure reasoning, Argon outperforms all other frontier models, with an 87% score.
To demonstrate these capabilities in action, we tested Argon’s ability to learn an out-of-distribution physical skill simply by watching. In an internal test, Argon watched a raw video of a human playing cornhole, mapped the spatial coordinates of the environment, and calculated the required whole-body joint movements. It then autonomously built the simulation code. When transferred onto Apptronik’s Apollo humanoid, the robot quickly sank seven consecutive shots in a real-world trial.
This "Video-to-Sim-to-Real" pipeline compresses weeks of manual simulation modeling into a few hours, transforming ordinary videos into a scalable, infinite training ground for robotics. Learn more about how this accelerates the pace of development in robotics in our developers blog.