AI News
官方更新 Anthropic News 2026-09-23T00:00 正文 ok 1985 words

Anthropic 推出模型硬件标准（MHS）研究预览版：让 AI Agent 安全操控实体科研与工业设备

英文标题：AnnouncementsAug 27, 2026Previewing the Model Hardware StandardWe’re opening a research preview of the Model Hardware Standard (MHS), a shared specification for AI agents to safely operate physical de

Anthropic 宣布向科研实验室与先进制造机构开放“模型硬件标准”（Model Hardware Standard，简称 MHS）的研究预览版，旨在为 AI Agent 操控实体硬件提供一套安全且标准化的通用规范。MHS 具备模型无关性并支持 MCP（Model Context Protocol）等协议，能够将过去需耗时数周甚至数月的跨设备集成缩短至数小时甚至几分钟，使 Agent 能同时调度显微镜、机械臂、移液机等设备执行复杂实验与全天候自动化工作流。早期合作案例表明，MHS 在量子计算机激光锁相故障恢复、高通量剂量反应实验及蛋白质测定等方面展现出显著成效；在正式开源前，Anthropic 将联合 AWS、Doosan Robotics、Hugging Face 等合作伙伴深化物理安全评测与最佳实践。
打开原文相关 3.6 · 机会 2
media76.8 KB media143.1 KB media48.7 KB media48.6 KB media130.4 KB media63.8 KB media437.8 KB media295.7 KB media34.9 KB media33.7 KB media128.4 KB media215.5 KB media30.5 KB media24.8 KB media37.7 KB media70.0 KB media73.0 KB media32.7 KB media62.6 KB media51.7 KB

中文

我们正面向首批科研实验室和先进制造企业开放**模型硬件标准（Model Hardware Standard，简称 MHS）**的研究预览版。这是一套用于让 AI Agent 安全操控物理设备的通用规范。MHS 使 AI Agent 能够并行操作多台实验室与生产设备——例如显微镜、液体处理工作站（移液器）和机械臂，并执行从常规药物发现实验到量子计算机激光校准等一系列精细任务。MHS 的研发始于 Anthropic 与 HHMI Janelia Research Campus 的合作。

在传统流程中，实验室或制造设施通常需要数周甚至数月的时间来安装和集成硬件。大多数设备之间无法直接通信，需要专业人员定制专用的集成方案。MHS 将此类集成工作大幅缩减至数小时或数分钟内。通过将 AI 深度融入这些工具中，MHS 还能帮助研究人员和工程师更轻松地调度全天候自主运行的实验和工作流；Agent 能够对实验的每个步骤进行推理、实时更新参数，甚至在某些情况下无需人工干预即可从硬件错误中恢复。

在将该标准正式开源之前，我们正在与科学、机器人、电子及制造领域的合作伙伴分享 MHS 的早期版本，以便协同构建安全评测体系并制定 AI 系统操作物理设备的最佳实践。MHS 适用于任何具有可编程接口的设备。它具备模型无关性（model-agnostic），任何 Agent 框架均可通过标准协议访问它，例如模型上下文协议（Model Context Protocol, MCP）。若需申请加入研究预览，请访问此处。

MHS 的工作原理

模型硬件标准（MHS）引入前后的对比。

在实验室或工厂车间中让多台设备协同通信本就极具挑战，更不用说将 AI 集成到这套环境中所带来的额外复杂性了。每台设备往往拥有独立的编程接口，此前业内一直缺乏标准化的集成方式。而且，即便设备已经实现物理连接，它们也缺乏向 AI Agent 共享数据的统一通道，更无法让 Agent 安全地执行操作。

MHS 通过引入标准化驱动程序（Driver）来解决这些挑战——即作为计算机操作系统与硬件设备之间转换桥梁的软件。MHS 驱动程序采用了一组简化的基础原语（primitives），包括“read”（例如“读取温度”）或“write”（例如“设置温度”）等任何硬件设备都能理解并执行的命令。同时，它以标准格式让各设备具备可发现性，使得设备和 Agent 能够在网络中相互发现并直接通信，不再需要中间定制的“翻译”程序。

此外，MHS 驱动程序还能帮助 AI Agent 理解如何使用它从未见过的全新设备，为其提供仅凭代码本身可能无法获知的机器物理特性（例如机械臂的自重，这对于掌握如何安全操纵机械臂至关重要）。迄今为止，此类信息大多停留在纸质手册、用户电脑中，或是作为技术人员的隐性知识存在。而在 MHS 驱动程序中，用户可以直接使用自然语言标签写入这些信息（用户可以自行编写，也可以通过与 Agent 对话，由 Agent 针对硬件配置进行访谈式录入）。利用这些标签信息，MHS 驱动程序会自动生成一份参考文件，包含设备的一般特性（如测量范围、可调节参数以及强制执行的安全限制等）。这份文件为 Agent 提供了安全操作该设备所需的全部上下文。

在设备连接完毕且 Agent 掌握了每台设备的使用方法后，Agent 需要具体的控制途径。在 MHS 中，主要通过三种机制实现：MCP、命令行界面（CLI）和代码文件（API）。三者协同工作，使得开发者只需单行代码即可完成跨多设备的联动编排。

一旦 Agent 获得了设备控制权，它就能接收每台设备的运行数据，并在宏观层面上对整体任务进行监督与调度。Agent 可以按顺序编排跨仪器的实验步骤，实时监控结果，并在环境条件改变时动态调整参数。当 Agent 需要执行长周期任务，或需要以超出自身在线推理速度的频率高频操作设备时，它可以将来自一台或多台设备的驱动指令在代码文件中进行链式串联。这样一来，硬件设备便可自主执行既定流水线操作，无需 Agent 在每一步中都重新推理。

在测试 MHS 期间，我们发现 Claude 能够以类似于科研人员的探索性方式与实验及硬件进行交互。例如，我们曾观察到 Claude 调节激光器后，通过摄像头观察反射结果以评估激光束的偏移情况，并反复迭代该过程以摸清事件之间的因果因次。随后，Claude 将其探索出的规律封装为代码文件，编写了一段确定性脚本，使其无需步步推理即可自主完成激光对准，最终让整个流程以单条指令的形式高速执行。

MHS 的早期实践案例

我们目前所见到的前沿模型与 MHS 的结合才刚刚起步，但我们希望该标准能够帮助各个领域的研究人员、工程师及从业者，在任何拥有可编程接口设备的场景下加速科学发现与实验探索。

在研发 MHS 的过程中，我们已将其共享给了生物科技、机器人、量子计算等领域的若干实验室和硬件制造商。在这些早期项目中，我们见证了 MHS 显著缩减设备集成时间、在多种实验场景下大幅加快迭代速度，并在机器实时运行调度与实时故障排查中发挥了关键辅助作用。以下是我们合作伙伴分享的部分早期项目细节：

基因泰克（Genentech）：应用 MHS 实现实验室自动化

基因泰克的研究人员部署并测试了 MHS，将其作为自动化 BCA 蛋白质定量测定的概念验证方案。BCA 测定是测量样本中总蛋白浓度的标准流程，需要液体处理工作站、机械臂和酶标仪之间的精密协作。

华盛顿大学 Baker 与 Pinglay 实验室：将 AI Agent 带入实验台

华盛顿大学 Baker 与 Pinglay 实验室的博士生 Zihao Song 利用 MHS 构建了一套用于远程监控实验仪器的仪表盘；打造了一套由 AI Agent 监督的 qPCR 实验系统（通过加热与冷却循环扩增靶标 DNA），该系统可实时监视扩增曲线并在最佳时机终止实验；并实现了机械臂与移液机之间的无缝集成，达成无碰撞的微孔板自动化交接。

卡耐基梅隆大学：通过快速自动化测定剂量反应曲线

卡耐基梅隆大学的研究人员使用 MHS 将梯度稀释剂量反应实验的运行速度提升了约 3 倍。AI Agent 统一编排了分布在三台运行不同底层接口计算机上的液体处理设备、酶标仪、机械臂和监控摄像头。

HHMI Janelia：利用 MHS 加速显微成像研究

在 HHMI Janelia Research Campus，研究人员正使用 MHS 加速一系列与显微镜成像相关的项目。在此，来自 Ahrens 实验室（研究睡眠如何帮助身体从压力中恢复）的科学家 Virginie Ruetten 分享了她如何利用 MHS 统一并调度此前涉及 7 套完全没有通用接口的不同供应商软件系统的复杂实验台。

QuEra Computing：将 MHS 用于量子激光稳频

中性原子量子计算公司 QuEra 利用 MHS 赋予 AI Agent 对其量子机器内部激光系统部分组件的控制权。该 Agent 研发出的控制器能够在无需人工干预的情况下，以 99.3% 的成功率恢复激光的“锁频”（激光与原子发生相互作用所必须保持的超高精度频率）。

Tetsuwan Scientific：利用 MHS 运行 qPCR 监测本地污染

Tetsuwan 的研究人员将 MHS 集成到了其自动化生物实验室平台 ResearchOS 中。MHS 协助编排了一套 qPCR 工作流，为加州圣佩德罗溪（San Pedro Creek）污染特征分析的公民科学行动提供了支持。

此外，众多硬件厂商及其配套软件开发商也正在为其设备加入 MHS 支持，使 AI Agent 能够更容易地发现并操控其产品。例如：

  • Amazon Web Services (AWS) 将通过其用于连接 AI Agent 与实体设备的开源库 Strands Robots 全面支持 MHS。AWS 将在 MHS 研究预览期内向参与者提供 Strands Robots 软件包的内测预览版本。
  • Automata 正在为其实验室自动化平台 LINQ 引入 MHS 支持，以在自主实验室中实现对各类仪器的智能错误恢复与处理。
  • **丹纳赫（Danaher）**与 Anthropic 正积极探索如何利用 MHS 支持的能力赋能其智能仪器与自主实验室，从而扩大生物医药研发规模。
  • **斗山机器人（Doosan Robotics）**正在其机械臂产品上测试 MHS，包括执行自动化质量检测以及跨多机器人协同作业编排。
  • MBF Bioscience 正在为其 ScanImage 软件构建 MHS 驱动程序。全球数百家神经科学实验室均采用该软件驱动激光扫描显微镜，此举将使 AI Agent 能够融入实时数据分析和活体实验中。
  • **凯杰（QIAGEN）**在其 QIAsymphony Connect 核酸纯化平台上通过可运行的概念验证对 MHS 进行了测试，验证了 AI Agent 如何协助实验室更快排查设备故障、引导操作人员完成系统恢复，并在降低生物样本污染风险的同时提升仪器正常运行时间。
  • **帝肯（Tecan）**正在为其 Fluent 液体处理工作站平台增加 MHS 支持，以便 AI Agent 能够直接发现并控制该设备。
  • **优傲机器人（Universal Robots）**已获得 MHS 的早期访问权限，并计划在其机器人平台上加入对该标准的支持。

加入研究预览

合作伙伴取得的这些早期成果令人振奋，但在正式开源该标准之前，我们仍有许多工作要做。作为大型语言模型，Claude 是通过文本和图像来认识物理世界的，这意味着它的空间与物理推理能力仍存在局限性，依然需要人类专家的监督。例如在处理蛋白质样本时，基因泰克的研究人员必须引导 Claude 认识到样本起泡所导致的错误属于物理故障而非软件 Bug，并且只能通过正确的物理干预手段予以解决。

此外，MHS 目前尚无法直接适用于完全缺乏可编程接口的硬件，因此我们正在与相关设备制造商合作内置 MHS 驱动程序。目前许多开发者已经在使用 Claude Code 与单独的物理设备进行交互；在 MHS 的下一阶段，我们希望将该标准扩展至更多开发者赖以构建应用的设备上。早期适配者包括 Hugging Face（正为其机器人库 LeRobot 添加 MHS 支持）以及树莓派（Raspberry Pi）（在成功完成树莓派摄像头 MHS 驱动测试后，正推进其多款产品的 MHS 集成）。

我们还将利用此次研究预览与初始合作伙伴一道构建补充性的安全评估体系，强化 AI 应用于实体物理世界中的防护措施。我们正在制定一份物理安全路线图，以进一步完善防护政策并扩大应对滥用风险的覆盖范围。在 MHS 正式开源时，我们将发布研究预览期的实践总结，作为安全部署该标准的权威指导指南。

我们现诚挚邀请各行各业的利益相关方加入 MHS 研究预览候补名单。若您有意参与，请在此提交申请。

致谢

MHS 最初由 Anthropic 有益部署团队（Beneficial Deployments team）的 Alek Kemeny 与 HHMI Janelia Research Campus 的博士后科学家 Arco Bast 合作发起。当时 Bast 正在一套复杂的脑成像实验台上开展实验，该设备整合了来自不同供应商的激光器、电动聚焦器和专用相机，彼此缺乏通用接口。为了加速其实验，他开发了一套共享内存字典，使各仪器能够以内存级速度相互通信。随后，Kemeny 与 Bast 携手将 AI 模型深度接入该接口。

我们衷心感谢迄今为止为该项工作做出贡献的每一位成员，包括但不限于 Aaron Boswell、Ben Arthur、Boaz Mohar、Gagan Bhat、Mark Kittisopikul、Nadine Yasser、Nick Purcell、Takashi Kawase 以及 Virginie Ruetten。我们期待与行业伙伴以及即将迎来的开源社区共同推动 MHS 的演进与发展。

English / 原文

We’re opening a research preview of the Model Hardware Standard (MHS), a shared specification for AI agents to safely operate physical devices, to a first group of scientific research labs and advanced manufacturers. MHS enables AI agents to operate multiple lab and manufacturing instruments, such as microscopes, liquid handlers, and robotic arms, in parallel, and perform intricate tasks ranging from routine drug discovery experiments to laser calibration on a quantum computer. The development of MHS began as a collaboration between Anthropic and HHMI Janelia Research Campus.

It typically takes a lab or manufacturing facility weeks, if not months, to set up and integrate their hardware. Most devices don’t communicate with each other, instead requiring specialists to build bespoke integrations. MHS reduces this integration work to hours or minutes. And by incorporating AI into these tools, MHS also helps researchers and engineers more readily orchestrate autonomous, round-the-clock experiments and workflows, with agents able to reason through each step in an experiment, update parameters in real time, and, in some cases, recover from hardware errors without intervention.

We’re sharing an early version of MHS with partners across science, robotics, electronics, and manufacturing so we can collaborate to build safety evaluations and develop best practices for AI systems operating physical equipment, ahead of making the standard open source. MHS works with any device that has a programmable interface. It is also model-agnostic, and any agent harness can access it using standard protocols, such as the Model Context Protocol. To apply for access to the research preview, head here.

How MHS works

Before and after the Model Hardware Standard (MHS).

Getting multiple devices in a lab or on a factory floor to communicate with one another can be challenging, even setting aside the added difficulty of integrating AI into the setup. Each device tends to have its own programming interface, and so far there has been no standardized way to integrate them. And once the devices are connected, there is no common way for them to share data with an AI agent, nor to let the agent operate them safely.

MHS addresses these challenges by introducing a standardized driver: software that translates between a computer’s operating system and a hardware device. The MHS driver uses a simple set of primitives—commands like “read” (for example, “get temperature”) or “write” (for example, “set temperature”)—that any hardware device can understand and act on. And it makes each device discoverable in a standard format, so that devices and agents can find each other and communicate across networks without needing a bespoke “translator” program in between.

The MHS driver also helps an AI agent understand how to use a device it has never seen before, giving it information about machine characteristics that may not be discernable from code alone (for example, the weight of a robot arm, which is important for knowing how to manipulate it safely). To date, much of this information has been stored in paper manuals, on a user’s computer, or as tacit knowledge. But the MHS driver contains tags that let the user write this information directly in natural language (users can either do this themselves, or by chatting to an agent that interviews them about their hardware setup). With the information from these tags, the MHS driver then automatically produces a reference file with information about a device’s general characteristics, such as what it can measure, what can be adjusted, and what safety limits will be enforced. This file gives the agent everything it needs to know to operate the device.

After the devices are connected and the agent knows how to use each one, the agent needs a way to control the hardware. For MHS, there are three such mechanisms: MCP, the command line interface, and code files (APIs). These work together to enable orchestration across multiple devices via a single line of code.

Once the agent can control the devices, it’s able to receive operating data from each one and supervise and direct the work at a high level. The agent can sequence steps across instruments, monitor results, and adjust parameters as conditions change in real time. When the agent needs to execute long-running tasks or operate devices faster than its online reasoning would allow, it can chain together driver commands from one or more devices in code files. This allows the devices to carry out operations themselves, without the agent needing to reason at every step.

As we’ve tested MHS, we’ve found that Claude interacts with experiments and hardware in an exploratory manner, much as a scientist would. For example, we observed Claude make an adjustment to a laser, observe the results through a camera to assess how its adjustment moved the laser beam, and repeat the process, seeking to understand the sequence of events. Claude then packaged what it learned into code files, writing a deterministic script that let it align the laser without having to reason at each step, so the whole process could run as a single command.

Early examples from MHS

We are only just beginning to see what people can do with frontier models and MHS, but our hope is that the standard can be of use to researchers, engineers, and other practitioners in speeding up the process of discovery and experimentation in any domain that uses devices with a programmable interface.

As we developed MHS, we shared it with a handful of labs and hardware manufacturers in biotech, robotics, quantum computing, and other fields. Across these early projects, we saw MHS reduce the time it took to integrate devices, make it possible to iterate faster in a variety of experimental settings, and assist with the live operation of machines and real-time fault detection. Below, our partners share the details of some of their early projects involving MHS.

Genentech: Implementing MHS for lab automation

Researchers at Genentech implemented and tested MHS as a proof-of-concept for automating the BCA protein assay, a standard procedure to measure total protein concentration in a sample, which requires coordinating across a liquid handler, a robotic arm, and a plate reader.

University of Washington Baker and Pinglay labs: Bringing AI agents to the bench

Zihao Song, a PhD student in the University of Washington Baker and Pinglay labs, used MHS to build a dashboard to remotely monitor his instruments; an AI agent-supervised qPCR (which copies a target DNA sequence through repeated cycles of heating and cooling) that watches amplification curves and halts the procedure at the right moment; and an integration between a robotic arm and a liquid handler for collision-free plate handoffs.

Carnegie Mellon University: Determining dose-response curves through rapid automation

Researchers at Carnegie Mellon University used MHS to run serial dilution dose-response experiments about three times faster than before, with an AI agent orchestrating a liquid handler, a plate reader, a robotic arm, and monitoring cameras spread across three computers with fundamentally incompatible interfaces.

HHMI Janelia: Using MHS to accelerate microscopy research

At HHMI Janelia Research Campus, researchers are using MHS to speed up a range of microscopy-related projects. Here, Virginie Ruetten, a scientist in the Ahrens lab who studies how sleep helps the body recover from stress, shares how she used MHS to unify and orchestrate a rig that previously involved seven different vendor programs without a shared interface.

QuEra Computing: Using MHS in quantum laser stabilization

QuEra, a company that builds quantum computers using neutral atoms, used MHS to give an AI agent control over parts of the laser system inside its quantum machines. The agent developed a controller that recovers the laser’s “lock”—the ultra-precise frequency the lasers must hold to interact with the atoms—99.3% of the time without human intervention.

Tetsuwan Scientific: Using MHS to run qPCRs to profile local pollution

Researchers at Tetsuwan integrated MHS with its automated biology lab platform, ResearchOS. MHS helped orchestrate a qPCR workflow to contribute to citizen science efforts to characterize pollution in California’s San Pedro Creek.

Hardware vendors and the software companies that support them are also building MHS support into their equipment so AI agents can more easily discover and operate their devices. For example:

  • Amazon Web Services will support MHS through Strands Robots, the library for connecting AI agents to physical devices. AWS will provide participants a private, pre-release version of the Strands Robots package for the duration of the MHS research preview.
  • Automata is adding MHS support to LINQ, their lab automation platform, to perform intelligent error handling of instruments in autonomous labs.
  • Danaher and Anthropic are actively exploring how MHS-supported capabilities could enable its smart instruments and autonomous laboratories to scale biomedical research and development.
  • Doosan Robotics is testing MHS with their robotic arms, including to perform automated quality assurance and coordinate tasks across multiple robots.
  • MBF Bioscience is building an MHS driver for ScanImage, the software that runs laser-scanning microscopes in hundreds of neuroscience labs worldwide, to integrate AI agents into real-time data analysis and experiments.
  • QIAGEN is experimenting with MHS through a working proof-of-concept on its nucleic acid purification platform, QIAsymphony Connect, showing how AI agents could help laboratories troubleshoot instrument issues faster, guide operators through recovery, and improve instrument uptime while reducing risk to biological samples.
  • Tecan is adding MHS support for their Fluent liquid handling platforms so AI agents can discover and operate them directly.
  • Universal Robots has had early access to MHS and plans to add support to its robotics platform.

Joining the research preview

These early results from our partners are encouraging, but we have more work to do on the standard before we open-source it. As a large language model, Claude learns about the physical world through text and images, meaning its spatial and physical reasoning have limitations that still require expert oversight. When working with protein samples, for example, Genentech researchers had to guide Claude to recognize that errors caused by foaming in samples were physical failures, not software bugs, that could only be mitigated through the appropriate physical corrections.

MHS also doesn’t yet work with hardware that lacks a programming interface, so we’re working with the manufacturers of such devices to build in MHS drivers. Many developers already use Claude Code to work with individual pieces of physical equipment; for the next phase of MHS, we hope to expand the standard to cover more of the devices developers build on. Early adopters include Hugging Face, who are adding MHS support in LeRobot, their robotics library, and Raspberry Pi, who are enabling MHS integration across a number of their products following successful tests using their Camera MHS Driver.

We will also use the research preview to build additional safety evaluations with our launch partners and strengthen protections for the use of AI in the physical world. We are developing a physical safety roadmap to further bolster our safeguards policy and enforcement coverage against the risk of misuse. When we open-source MHS, we will release findings from the research preview as part of our guidance for deploying the standard safely.

We’re inviting stakeholders across industries to join the waitlist for our research preview of MHS. If you’d like to participate, submit your interest here.

Acknowledgments

MHS began as a collaboration between Alek Kemeny on Anthropic’s Beneficial Deployments team and Arco Bast, a postdoctoral scientist at HHMI Janelia Research Campus. Bast was running complex brain-imaging experiments on a rig that combined lasers, motorized focusers, and specialized cameras from different vendors with no common interface. To speed up his experiments, he developed a shared memory dictionary that enabled the instruments to communicate with one another at memory speed. Kemeny and Bast worked together to integrate AI models into that interface.

We thank everyone who has contributed to this work so far, including, but not limited to, Aaron Boswell, Ben Arthur, Boaz Mohar, Gagan Bhat, Mark Kittisopikul, Nadine Yasser, Nick Purcell, Takashi Kawase, and Virginie Ruetten. We look forward to moving MHS forward with our industry partners and, soon, with the open-source community.