内容来源：https://research.google/blog/grounding-ai-agents-in-biological-reality-building-blocks-for-autonomous-wet-labs/

内容总结：

谷歌研究团队近日发布三项研究进展，展示其将人工智能代理引入湿实验室环境，通过闭环学习加速生物分子发现。相关研究由谷歌研究科学家普贾·拉奥、软件工程师佩塔尔·西尔科维奇和安娜莉莎·帕夫洛斯基主导，旨在让AI代理不仅能够提出假设和分析数据，还能实际操作实验室机器人完成实验、从结果中学习并自我改进，最终发现针对癌症靶点的个位数纳摩尔级蛋白质结合物。

研究团队指出，实现这一愿景需解决两大挑战：一是前沿模型在三维几何和物理状态推理方面仍不可靠，难以安全操控移液机器人等实验室设备；二是AI假设生成和计算设计进展迅速，但湿实验室实验验证速度未能同步，成为瓶颈。

为此，团队推出三个核心项目。第一，VERID框架——实验室工作单元的语义数字孪生系统，可实时追踪从机械臂几何结构到每个孔板体积、试剂身份和移液枪头库存等全部状态。该框架建立在开源PyLabRobot基础上，能判断命令在物理、逻辑和科学层面是否可行。案例研究显示，系统可捕捉因移液过近孔底导致的染料分层、在读板机故障后无需重新移液即可恢复运行、在模拟器拒绝物理上不可行的操作时即时重新规划，并通过闭环自我对弈将染料混合物重建准确率提升五倍以上。

第二，以DNA适配体为模式系统的闭环代理分子发现。适配体设计-测试-分析周期仅需7至10天，因为DNA可化学合成并通过测序直接读取。在两个靶点蛋白上经过三轮迭代，AI驱动的理性与从头设计将确认命中率分别提升至肌红蛋白33.5%和α-凝血酶42.1%。研究还发现，代理能像科学家一样分析数据并调整实验方案，同时也会探索结构生物学家通常不会关注的序列空间。

第三，代理引导的表位切除实现经济型从头结合物设计。针对在实体瘤中过表达的成纤维细胞活化蛋白α，研究团队通过手术式切除折叠过程中的局部结合口袋，将每轮计算周期加速八倍以上而不损失结构精度。在同等算力下，人机协作将近乎将计算命中率翻倍，并覆盖更广泛的靶点位点。实验仅数轮即获得个位数纳摩尔级亲和力的结合物，达到通常需大量实验室优化才能实现的类药物结合水平。团队还建立了酵母表面展示与荧光激活细胞分选的高通量筛选流程。

在安全方面，团队依据谷歌前沿安全框架和生物韧性方针，在计算和湿实验室两端均设置保障措施，包括确保代理优化真实靶点结合而非实验捷径、验证多步骤实验方案、持续监控代理推理与执行轨迹。

研究团队表示，这些努力构成了人类主导的生命科学自主发现的基石，下一步将把VERID的可追溯自动化与蛋白质发现闭环学习相结合，使代理能够直接在湿实验室中导航复杂的生物搜索空间。

中文翻译：

2026年10月16日
Pooja Rao，研究科学家；Petar Sirkovic，软件工程师；Annalisa Pawlosky，研究科学家；Google

我们正在将AI智能体引入Google Research的湿实验室工作台，以探索复杂的生物学空间。通过将智能体与物理实验室机器人相结合，我们能够运行快速的闭环分子设计循环，让智能体学会如何学习，最终发现针对癌症靶点的个位数纳摩尔级蛋白质结合体。

前沿AI系统有潜力通过智能地探索庞大的组合搜索空间（例如，一个仅100个氨基酸的蛋白质就涵盖至少20^100种可能的序列），需要进行动态的多候选探索，从而变革生物学研究和药物发现。我们的长期研究愿景是：AI智能体不仅能提出构想和分析，还能运行实验室实验来验证其假设、从结果中学习并自我改进以解决复杂问题——这一切都由人类科学能动性驱动。

实现这一愿景需要解决两个相互交织的挑战：第一，前沿模型仍然无法可靠地对三维几何和物理状态进行推理——这在自动化专用液体处理机器人时构成问题，这些机器人负责在湿实验室中移动试剂、追踪体积并执行分子生物学方案。第二，尽管智能体假设生成和计算机模拟设计正在快速发展，需要反复的真实世界反馈循环来验证提议并穿越庞大的搜索空间，但真实世界的湿实验室实验却未能跟上步伐，使实验读数比以往任何时候都更加成为瓶颈。

在这篇文章中，我们分享三个研究项目，重点介绍我们在弥合计算机模拟AI探索与真实世界湿实验室实验之间差距方面的进展：

第一，我们提出“发现实验室验证基础设施”（VERID）框架，以弥合AI智能体的高层推理与湿实验室复杂且易出错的物理现实之间的差距。它是实验室工作单元的语义数字孪生，即一个实时的、有状态的3D体积实体树，追踪从机械臂几何结构到单个孔板体积、试剂身份和移液枪头库存的一切信息。

命令的安全性取决于实时物理上下文以及代码本身。智能体可以生成语法上有效但在物理上不可能执行的代码（例如，将8通道移液器降入一个太短的窄槽中）、在物流上无效的操作（例如，从已耗尽的孔中吸取液体），或因未建模的流体效应而在科学上存在缺陷的操作。

VERID构建在开源PyLabRobot框架之上，提供四项核心能力：

在我们的报告中，我们通过案例研究展示了这些能力的实际应用。首先，同步视频和执行轨迹捕捉到了因分液过于靠近孔底而导致的不均匀染料分层现象，使智能体能够改进其混合策略。在同一轮实验中，持久化的数字孪生状态使智能体能够在读板机故障后于运行中途恢复，而无需重新移液。其次，当模拟器拒绝了一个物理上无法放入窄槽的8通道吸液操作时，智能体即时重新规划，并设计了一个有针对性的析因诊断方案，分离出由枪头壁残留携带造成的细微偏差——这是仅靠重复实验无法发现的。最后，在一个闭环自我对弈实验中，智能体迭代设计和运行机器人实验，从俯拍摄像头图像中重建盲法染料混合物，在多次运行中识别自身的光学和流体伪影，将准确率提高了五倍以上。

可复现的执行和完整轨迹日志——捕获驻留时间、蒸发和孔板布局等过程变量——为智能体奠定了基础，使其最终能够在多轮并行探索和优化大量候选物时，将生物信号与实验噪声区分开来。

智能体需要真实的实验读数来改进其假设，因为计算模型无法捕捉湿实验室反应中发生的全貌，也无法替代经验验证。在“适配体作为实验室闭环智能体分子发现的沙盒”一文中，我们使用蛋白质结合DNA适配体，在3个设计-测试-迭代循环中与AI智能体闭环原型化实验室流程。适配体发现是临床生物标志物发现研究中常见的一类实验。一个完整的适配体设计-测试-分析循环仅需7至10天，因为DNA可以通过混合文库化学合成并直接通过测序读取。在每一轮中，智能体设计候选序列，这些序列在磁珠上与靶标蛋白进行筛选以分离功能性结合体，然后测序以返回丰富的定量数据供下一循环使用。

在两个难度不同的蛋白质靶标（肌红蛋白和α-凝血酶）上进行的三轮实验中，AI驱动的理性设计和从头设计提高了确认的靶向命中率，如下图所示（肌红蛋白和α-凝血酶分别达到33.5%和42.1%），尽管每个靶标都需要识别并克服不同的湿实验室失败模式。

在α-凝血酶上，第1轮产生了0%的结合体，因为固定引物悬垂破坏了48%序列的折叠；当智能体在第2轮引入夹钳式侧翼茎结构并在第3轮进行多样化后，命中率攀升至26.0%，然后在98.5%特异性下达到42.1%。

在肌红蛋白上，由于智能体在第2轮优先考虑原始结合亲和力，它们大量富集了G-四链体基序（占设计的63%）。虽然原始拉下实验信号增加，但湿实验室数据显示大多数这些G-四链体是非特异性的“黏性”结合体，附着在脱靶蛋白和裸磁珠上，导致靶标特异性（从75.0%降至19.1%）和真实的、经磁珠校正的命中率（从10.2%降至3.7%）均大幅下降。智能体从第2轮读数中识别出这一伪影后，自主修订了第3轮的设计规则，限制混杂基序、扣除磁珠结合体，并转向非G4结构支架，从而恢复了特异性（72.4%）并使靶向命中率飙升九倍（33.5%）。

在论文中，我们还研究了智能体如何像科学家一样推理，分析数据并提出对湿实验室方案的调整建议，但有时也会以非典型方式思考，探索结构生物学家可能不会涉足的序列空间。

蛋白质的闭环更为复杂。与化学合成的适配体不同，蛋白质必须通过生物学方式表达，因此每个循环都增加了细胞或无细胞选择、表达和折叠步骤。加上更大的序列空间，这在计算和湿实验室两侧都造成了瓶颈。

在“智能体引导的表位切除实现经济的从头结合体设计”一文中，我们将工作流程应用于成纤维细胞活化蛋白α（FAP），这是一种在实体瘤中过表达的大型、具有挑战性的受体。仅经过少量实验运行，最优设计就产生了具有个位数纳摩尔亲和力的结合体，这种紧密的、类药物结合水平通常只有经过大量实验室优化轮次后才能实现。

在计算方面，从头结合体设计需要生成候选骨架、设计适配序列，并对所得复合物进行重新折叠以预测结合。最后的重新折叠步骤消耗了绝大部分GPU算力，因为它随靶标长度呈二次方增长。通过在折叠过程中精准切除仅局部结合口袋，我们的流程将每个循环加速了八倍以上，同时不损失结构精度。这将关于在哪里结合以及包含多少周围结构的决策转变为LLM智能体擅长优化的战术杠杆。

在同等算力下的头对头比较中，人机协作——由科学家设定高层策略、智能体驱动战术执行——将计算机模拟命中率几乎翻倍于科学家单独工作，同时在更广泛的靶标位点范围内发现了命中。为了将湿实验室筛选与我们的计算流程同步扩展，我们实现了酵母表面展示与荧光激活细胞分选（FACS）的操作化，该工作流程允许我们通过荧光并行筛选大型工程蛋白质变体文库。

我们的下一步是将这些线索编织在一起，将VERID完全可追溯的自动化与蛋白质发现的闭环学习相结合，使智能体能够直接在湿实验室中探索复杂、崎岖的生物学搜索空间。

根据Google的前沿安全框架和我们的生物韧性方法，我们在工作流程的计算和湿实验室两侧都建立了安全保障：

随着AI智能体承担更多设计-测试循环的工作，新的安全性和可靠性挑战随之出现。迈向自主湿实验室需要解决这些开放性问题，同时为人类能动性和监督提供机会：确保智能体优化的是真正的靶标结合而非无意的实验捷径、验证多步骤湿实验室方案，以及持续监控智能体的推理和执行轨迹。

从将智能体与物理实验室机器人相结合，到运行快速闭环适配体循环让智能体学会探索序列空间，再到发现个位数纳摩尔级蛋白质结合体，这些努力构成了人类主导的生命科学自主发现的基石。我们对这一进展感到兴奋，并期待分享接下来的成果。

本研究由Annalisa Pawlosky领导，Pooja Rao和Petar Sirkovic共同参与。我们要感谢支持这项工作的基础论文的合著者和合作者：Zach Cutts、John Coller、Rachel Chen、Mathias Bellaiche、Hua Tang、Ryder Easterlin和Dina Zverinski（适配体发现）；Jun Kim、Artiom Myaskovsky、Oscar Donosa、Jamie Rogers和Lawrence Chan（蛋白质设计）；以及Yves Delley、John Coller、Zach Cutts、Alexander Daryin、Mathias Bellaiche、Jun Kim、Oscar Donosa、Srinidhi Seshadri、Tanner Clary和Sandy Klemm，以及Xinyi Deng、Sanath Ramachandran和Jiawu Bi的额外技术和实验贡献（VERID自动化）。

我们深深感谢Reuven Sayag、Avinatan Hassidim、Ronit Levavi Morad、Yossi Matias和James Manyika的领导指导，以及Matthias Heiler、Burak Gokturk、Bill Jia和Pushmeet Kohli在整个研究过程中的支持。我们还感谢Shekoofeh Azizi、Andrew Carroll、Philip Q. Nelson、Yishay Mansour、Dan Popovici和Riccardo Pisoni的审阅和深刻反馈，Amanie Brik对该项工作的整体贡献，以及Udi Graff为本文提供的视觉设计和图形。

英文来源：

October 16, 2026
Pooja Rao, Research Scientist, Petar Sirkovic, Software Engineer, and Annalisa Pawlosky, Research Scientist, Google
We are bringing AI agents to the wet-lab bench at Google Research to navigate complex biological landscapes. By grounding agents in physical lab robotics, we can run fast closed-loop molecular design cycles where agents learn how to learn, ultimately discovering single-digit nanomolar protein binders for cancer targets.
Frontier AI systems have the potential to transform biology research and drug discovery by intelligently navigating vast combinatorial search spaces (e.g., a single 100-amino-acid protein spans at least 20100 possible sequences) calling for dynamic multi-candidate exploration. Our long-term research vision is that AI agents will not only ideate and analyze, but also run lab experiments to test their hypotheses, learn from the results, and self-improve to solve complex problems — all driven by human scientific agency.
Realizing this vision requires solving two intertwined challenges: First, frontier models still do not reason reliably about 3-dimensional geometry and physical state — which poses a problem in the automation of the specialized liquid-handling robots that move reagents, track volumes, and execute molecular biology protocols in a wet lab. Second, while agentic hypothesis generation and in-silico design are advancing rapidly, needing repeated cycles of real-world feedback to validate the proposals and navigate vast search spaces, real-world wet-lab experiments have not kept pace, making experimental readouts more of a bottleneck than ever.
In this post we share three research projects highlighting our progress on bridging the gap between in-silico AI exploration and real-world wet-lab experimentation:
First, we present the VERified Infrastructure for Discovery Laboratories (VERID) framework to bridge the gap between the high-level reasoning of AI agents and the complex, error-prone physical reality of a wet lab. It is a semantic digital twin of the laboratory workcell, i.e., a live, stateful 3D volumetric entity tree that tracks everything from robotic arm geometry to individual well volumes, reagent identities, and pipette tip inventory.
The safety of a command depends on the live physical context as well as the code. An agent can generate syntactically valid code that is physically impossible (e.g., lowering an 8-channel pipette into a narrow trough that is too short), logistically invalid (e.g., aspirating from a depleted well), or scientifically compromised by unmodeled fluidic effects.
Built on top of the open-source PyLabRobot framework, VERID provides four core capabilities:
In our report, we show these capabilities in action through case studies. First, synchronized video and execution traces caught uneven dye stratification caused by dispensing too close to the well floor, allowing the agent to refine its mixing strategy. In the same campaign, the persistent digital twin state allowed the agent to recover mid-run from a plate-reader failure without re-pipetting. Second, when the simulator rejected an 8-channel aspiration that physically wouldn't fit in a narrow trough, the agent replanned on the fly and designed a targeted factorial diagnostic isolating a subtle bias caused by residual tip-wall carryover that replication alone would have missed. Finally, in a closed-loop self-play campaign, an agent iteratively designed and ran robot experiments to reconstruct blinded dye mixtures from overhead camera images, identifying its own optical and fluidic artifacts across runs to improve accuracy more than fivefold.
Reproducible execution and full trace logs — capturing procedural variables like dwell times, evaporation, and plate layout — lay the groundwork for agents to eventually be able to separate biological signals from experimental noise as they explore and refine many candidates in parallel across rounds.
Agents need real experimental readouts to refine their hypotheses as computational models do not capture the full picture of what happens in a wet-lab reaction and cannot replace empirical validation. In “Aptamers as a sandbox for lab-in-the-loop agentic molecular discovery”, we use protein-binding DNA aptamers to prototype the lab in a closed loop with AI agents over 3 design-test-iteration cycles. Aptamer discovery is a type of experiment common in research efforts for clinical biomarker discovery. A complete aptamer design-test-analyze cycle takes just 7–10 days, as DNA can be chemically synthesized in pooled libraries and read out directly by sequencing. In each round, agents design candidate sequences, which are screened against target proteins on magnetic beads to isolate functional binders, and then sequenced to return rich quantitative data for the next cycle.
Across three rounds on two protein targets with varying difficulty levels (myoglobin and α-thrombin), AI-driven rational and de novo design raised confirmed on-target hit rates as can be seen in the image below (to 33.5% and 42.1% for myoglobin and α-thrombin, respectively), though each target required identifying and overcoming a different wet-lab failure mode.
On α-thrombin, Round 1 yielded 0% binders because fixed primer overhangs disrupted folding in 48% of sequences; once the agents introduced clamped flanking stems in Round 2 and diversified in Round 3, hit rates climbed to 26.0% and then 42.1% at 98.5% specificity.
On myoglobin, as agents prioritized raw binding affinity in Round 2, they heavily enriched G-quadruplex motifs (63% of designs). While raw pull-down increased, the wet-lab data showed that most of these G-quadruplexes were non-specific "sticky" binders adhering to off-target proteins and bare magnetic beads, causing both target specificity (from 75.0% to 19.1%) and true, bead-corrected hit rate (from 10.2% to 3.7%) to plunge. Recognizing this artifact from the Round 2 readout, the agents autonomously revised their design rules for Round 3, capping promiscuous motifs, subtracting bead binders, and pivoting to non-G4 structural scaffolds to recover specificity (72.4%) and surge ninefold in on-target hit rate (33.5%).
In the paper, we also examine how agents reason like scientists, analyzing data and suggesting tweaks to wet-lab protocols, but also sometimes think atypically, exploring sequence spaces that structural biologists might not.
Closing the loop for proteins is more complex. Unlike aptamers, which are chemically synthesized, proteins must be expressed biologically, so each loop adds cellular or cell-free selection, expression, and folding steps. Together with a larger sequence space, this creates bottlenecks on both the computational and wet-lab sides.
In “Agent-guided epitope excision enables economical de novo binder design”, we applied our workflow to fibroblast activation protein alpha (FAP), a large, challenging receptor overexpressed in solid tumors. In just a few experimental runs, the top designs yielded binders with single-digit nanomolar affinity, a level of tight, drug-like binding typically achieved only after extensive rounds of laboratory optimization.
Computationally, de novo binder design requires generating candidate backbones, designing sequences to fit them, and re-folding the resulting complexes to predict binding. That final re-folding step consumes the vast majority of GPU compute, as it scales quadratically with target length. By surgically excising just the local binding pocket during folding, our pipeline accelerated each cycle more than eightfold without losing structural accuracy. This turns decisions about where to bind and how much surrounding structure to include into tactical levers that LLM agents are well-suited to optimize.
In a head-to-head comparison at equal compute, human–agent collaboration, where a scientist sets the high-level strategy and an agent drives tactical execution, nearly doubled the in-silico hit rate of a scientist working alone while uncovering hits across a much broader range of target sites. To scale wet-lab screening alongside our computational pipeline, we operationalized yeast surface display with fluorescence-activated cell sorting (FACS), a workflow that allows us to screen large libraries of engineered protein variants in parallel by fluorescence.
Our next step is to weave these threads together, combining VERID’s fully traceable automation with closed-loop learning for protein discovery to enable agents to directly navigate complex, rugged biological search spaces in the wet lab.
In line with Google’s Frontier Safety Framework and our approach to bioresilience, we build safeguards across both the computational and wet-lab sides of our workflows:
As AI agents take on more of the design-test cycle, new safety and reliability challenges emerge. Moving toward an autonomous wet lab requires solving these open problems with opportunities for human agency and oversight: ensuring agents optimize for true target binding rather than unintended experimental shortcuts, verifying multi-step wet-lab protocols, and continuously monitoring agent reasoning and execution traces.
From grounding agents in physical lab robotics, to running fast closed-loop aptamer cycles where agents learn to explore sequence space, to discovering single-digit nanomolar protein binders, these efforts form the building blocks for human-directed autonomous discovery in the life sciences. We're excited by this progress and look forward to sharing what comes next.
This research is led by Annalisa Pawlosky, alongside Pooja Rao and Petar Sirkovic. We would like to thank our co-authors and collaborators across the foundational papers supporting this work: Zach Cutts, John Coller, Rachel Chen, Mathias Bellaiche, Hua Tang, Ryder Easterlin, and Dina Zverinski (aptamer discovery); Jun Kim, Artiom Myaskovsky, Oscar Donosa, Jamie Rogers, and Lawrence Chan (protein design); and Yves Delley, John Coller, Zach Cutts, Alexander Daryin, Mathias Bellaiche, Jun Kim, Oscar Donosa, Srinidhi Seshadri, Tanner Clary, and Sandy Klemm, with additional technical and experimental contributions from Xinyi Deng, Sanath Ramachandran and Jiawu Bi (VERID automation).
We are deeply grateful to Reuven Sayag, Avinatan Hassidim, Ronit Levavi Morad, Yossi Matias, and James Manyika for their leadership guidance and to Matthias Heiler, Burak Gokturk, Bill Jia and Pushmeet Kohli for their support throughout this research. We also thank Shekoofeh Azizi, Andrew Carroll, Philip Q. Nelson, Yishay Mansour, Dan Popovici, and Riccardo Pisoni for their reviews and insightful feedback, Amanie Brik for overall contributions to the effort, and Udi Graff for visual design and graphics for this post.