AI coding agents taught robots how to install GPUs and cut zip ties
AI coding agents taught robots how to install GPUs and cut zip ties
AI 编程智能体教会机器人安装 GPU 和剪扎带
What happens when you give AI coding agents a lab full of robotic arms, some compute resources, and a “generous token budget” for teaching the robots various tasks? The agents can apparently figure out a training regimen that teaches the robots to successfully cut zip ties and even insert GPUs into thin sockets on motherboards. 当你给 AI 编程智能体配备满屋子的机械臂、一些计算资源,以及用于教导机器人完成各种任务的“慷慨 Token 预算”时,会发生什么?显然,这些智能体能够摸索出一套训练方案,教会机器人成功剪断扎带,甚至将 GPU 插入主板上的狭窄插槽中。
That glimpse into how AI can act in a fully autonomous way to automate robot training was made possible by a new agent harness framework—software that wraps around AI models to enable their use of various tools while also providing capabilities such as memory, context, constraint, and feedback loops. 这种 AI 如何以完全自主的方式实现机器人训练自动化的尝试,得益于一种新的智能体框架(agent harness framework)——这是一种包裹在 AI 模型周围的软件,使其能够使用各种工具,同时提供记忆、上下文、约束和反馈循环等功能。
That agentic harness, called ENPIRE, was developed by robotics researchers at the Nvidia GEAR (Generalist Embodied Agent Research) lab alongside collaborators from Carnegie Mellon University in Pittsburgh and the University of California, Berkeley. 这种名为 ENPIRE 的智能体框架是由英伟达 GEAR(通用具身智能体研究)实验室的机器人研究人员,与匹兹堡卡内基梅隆大学以及加州大学伯克利分校的合作者共同开发的。
“A part of our NVIDIA GEAR lab now self-improves tirelessly overnight,” wrote Jim Fan, director of AI at NVIDIA, in a LinkedIn post. “We just read the reports in the morning.” Fan also jokingly described the goal of such AI-directed robot training, saying, “We all take a holiday and Jensen wouldn’t even notice,” in reference to Nvidia founder and CEO Jensen Huang. “我们 NVIDIA GEAR 实验室的一部分现在正彻夜不休地进行自我改进,”英伟达 AI 总监 Jim Fan 在 LinkedIn 上写道,“我们早上只需要读读报告就行了。”Fan 还开玩笑地描述了这种 AI 指导机器人训练的目标,称“我们都可以去度假,而黄仁勋甚至都不会注意到”,他指的是英伟达创始人兼 CEO 黄仁勋。
But it’s not only Nvidia robotics researchers who could benefit—Fan said the team would be open-sourcing everything so anyone can host their own “self-running robot lab at home.” 但受益的不仅仅是英伟达的机器人研究人员——Fan 表示,团队将开源所有内容,以便任何人都能在家中搭建自己的“自动运行机器人实验室”。
The ENPIRE harness has four modules that enable AI coding agents to perform automatic reset and verification on tasks, refine policies that guide robotic behavior, evaluate such policies across multiple physical robots working in parallel, and address failures by analyzing logs, ingesting research papers, and improving training infrastructure and algorithm code. More technical details are available in the research paper uploaded on June 16, 2026. ENPIRE 框架包含四个模块,使 AI 编程智能体能够对任务执行自动重置和验证,优化指导机器人行为的策略,评估跨多个并行工作的物理机器人的策略,并通过分析日志、吸收研究论文以及改进训练基础设施和算法代码来解决故障。更多技术细节可在 2026 年 6 月 16 日上传的研究论文中找到。
The harness was tested with three different AI coding agents, including OpenAI’s Codex with GPT-5.5, Anthropic’s Claude Code with Opus 4.7, and Moonshot AI’s Kimi Code with Kimi K2.6. Teams of the coding agents independently developed different algorithmic approaches to robot training, tested them in real-world experiments, and then retained whatever changes helped raise the overall success rate over repeated cycles of self-directed testing. 该框架通过三种不同的 AI 编程智能体进行了测试,包括 OpenAI 的 Codex(基于 GPT-5.5)、Anthropic 的 Claude Code(基于 Opus 4.7)以及月之暗面(Moonshot AI)的 Kimi Code(基于 Kimi K2.6)。编程智能体团队独立开发了不同的机器人训练算法方法,在现实实验中进行了测试,并在反复的自主测试周期中保留了有助于提高整体成功率的改进措施。
The success and limits of AI-directed robot training
AI 指导机器人训练的成功与局限
Equipped with ENPIRE, the AI coding agents developed strategies for robotic self-improvement that achieved a 99 percent success rate across several manipulation tasks, including the standard “Push-T” task that challenges robots to move a T-shaped block to fit a target position on top of a table. Other tasks included organizing pins in a pin box, tying and cutting zip ties, and placing a GPU into a motherboard before unplugging the graphics card again to reset for the next trial. 在 ENPIRE 的加持下,AI 编程智能体开发出了机器人自我改进策略,在多项操作任务中实现了 99% 的成功率,其中包括标准的“Push-T”任务,即挑战机器人将一个 T 型块移动到桌子上的目标位置。其他任务还包括整理销钉盒中的销钉、捆扎和剪断扎带,以及将 GPU 插入主板,然后再拔出显卡以重置进行下一次试验。
The most promising result may have come from the pin insertion and organization task. In that robot-training scenario, AI coding agents achieved nearly 100 percent success faster than a “frontier human-in-the-loop method” developed by many of the same human researchers. 最令人振奋的结果可能来自销钉插入和整理任务。在该机器人训练场景中,AI 编程智能体实现近 100% 成功率的速度,比同一批人类研究人员开发的“前沿人机协作方法”还要快。
Such experiments also showed how larger teams of up to eight AI coding agents could achieve high success rates in robot training more quickly than smaller four-agent teams or single agents working alone. For example, the eight-agent team achieved 99 percent success on the Push-T task in two hours of research time, compared to the four-agent team requiring three hours and the single-agent team requiring nearly five hours. 此类实验还表明,由多达八个 AI 编程智能体组成的大型团队,比四个智能体的小型团队或单个智能体独立工作能更快地在机器人训练中实现高成功率。例如,八智能体团队在两小时的研究时间内实现了 Push-T 任务 99% 的成功率,而四智能体团队需要三小时,单智能体团队则需要近五小时。
But the human researchers also discovered some crucial limitations when unleashing AI coding agents as autonomous robot trainers. The robots often sat idle and unused while the coding agents were busy “reading logs, writing code, debugging, or waiting for the language-model backbone.” Larger teams of coding agents also spent more time summarizing each other’s ideas and less time actually using the robots, and the coding agents sometimes failed to make full use of available compute resources when launching parallel training sessions. 但人类研究人员在将 AI 编程智能体作为自主机器人训练师使用时,也发现了一些关键的局限性。当编程智能体忙于“阅读日志、编写代码、调试或等待语言模型后端”时,机器人往往处于闲置状态。大型编程智能体团队也花费了更多时间总结彼此的想法,而用于实际操作机器人的时间较少;此外,编程智能体在启动并行训练任务时,有时无法充分利用现有的计算资源。
The faster success rates enabled through more agents and robots working together also came at the cost of higher token consumption—a noteworthy consideration at a time when AI developers such as Anthropic are weighing pricing changes that would significantly increase the token-related costs of using AI services. 通过更多智能体和机器人协同工作所带来的更快成功率,也以更高的 Token 消耗为代价——在 Anthropic 等 AI 开发商正在权衡可能大幅增加 AI 服务 Token 相关成本的定价调整之际,这是一个值得注意的考量因素。
Flush with cash from the AI boom, Nvidia has been busily pushing its vision for physical AI through multiple robotics initiatives. On May 31, the company announced a partnership with the prominent Chinese robotics company Unitree to provide a “Reference Humanoid Robot” for research labs developing general-purpose AI-powered robots. 凭借 AI 热潮带来的充裕资金,英伟达一直忙于通过多项机器人计划推动其物理 AI 的愿景。5 月 31 日,该公司宣布与中国知名机器人公司宇树科技(Unitree)建立合作伙伴关系,为开发通用 AI 机器人的研究实验室提供“参考人形机器人”。
During a whirlwind tour of South Korea in early June, Nvidia founder and CEO Jensen Huang also met with Hyundai Motor Executive Chair Chung Euisun to discuss scaling up the mass manufacturing of AI-powered robots. Hyundai Motor Group owns the US robotics company Boston Dynamics, which is already well-known for its four-legged “robot dog” Spot and has been working to commercialize its Atlas humanoid robot. 在 6 月初对韩国的旋风式访问期间,英伟达创始人兼 CEO 黄仁勋还与现代汽车执行董事长郑义宣会面,讨论扩大 AI 机器人的大规模制造。现代汽车集团拥有美国机器人公司波士顿动力(Boston Dynamics),该公司以其四足“机器狗”Spot 而闻名,并一直致力于将其 Atlas 人形机器人商业化。