Papers for
laboratory automation teams
Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.
Teleoperation improves fault recovery in self-driving laboratories
Toward Resilient Self-Driving Laboratories through Telerobotic Interventions
Abstract: Self-driving laboratories (SDLs) accelerate scientific research by integrating robotics, automated experimentation, and machine learning to execute experiments autonomously. Biology and chemistry have adopted these systems. However, increasing SDL complexity heightens susceptibility to unexpected faults in automated workflows, highlighting the need for efficient recovery mechanisms. In this study, we investigate telerobotic interventions to enhance SDL resilience against unexpected failures. We developed a teleoperation interface enabling human operators to resolve disruptions during automated tasks. The interface enables precise control of a six-degree-of-freedom (DOF) robotic arm (UR3e) using a 3D mouse (3Dconnexion SpaceMouse Pro). Two velocity-based controller strategies were evaluated: (i) a coupled mode mapping all six DOFs to the 3D mouse's central knob and (ii) a decoupled mode separating translational and rotational motions. To evaluate the framework, teleoperators intervened across three SDL fault scenarios. In the first study, comparative trials showed that the decoupled controller was associated with shorter completion times and reduced rotational motion. In a second study, teleoperators performed an aiming task with and without reference-path guidance. Users were more target-driven and risk-tolerant without guidance but showed behavioral differences under different guidance strategies. These findings suggest that controller configuration and reference-path design influence operator performance during SDL fault recovery, informing teleoperation interface optimization. This work demonstrates the potential feasibility of teleoperation as a human-in-the-loop recovery mechanism for SDL workflows, combining robotic precision with human adaptability and problem-solving. These findings also provide a foundation for future studies in shared autonomy and semi-autonomous intervention.
Artificial intelligence struggles to predict complex experimental outcomes accurately
Science Prediction Universe
Abstract: Humanity has long sought to explain natural phenomena. Reliable prediction of experimental outcomes is a central test of our understanding of the processes that produce them. If artificial general intelligence (AGI) is to surpass human scientific capabilities, it must also predict experimental outcomes more reliably than humans. Such capabilities could accelerate scientific discovery across disciplines, help address humanity's most pressing challenges, and improve human well-being. We introduce Science Prediction Universe (SPU), a benchmark of hidden experimental outcomes with 100 public verified tasks from chemistry, materials science, biology and medicine, and 16 private tasks from unpublished wet-lab experiments. Given an experimental setup and candidate conditions, an agent works with any resources it needs to rank the candidates by a measured outcome. We evaluate thirteen agent configurations spanning twelve frontier models across two harnesses (Codex and Claude Code). Current agents remain far from saturating wet-lab outcome prediction, with substantial performance disparities across models: on the public benchmark, configurations separate into two distinct tiers, with task-adjusted Spearman correlations ranging from 0.227 for the lowest-performing configuration to 0.478 for the best. Analysis of 1,155 scored public trajectories (227,103 tool calls) suggests that the bottleneck lies in scientific judgment rather than tool execution: agents rely on shared monotone priors, agreeing far more with one another than with experimental reality (0.52 vs. 0.33), and frequently compute trivial physical or chemical proxies that do not influence the final outcome.
AI agents struggle with rigorous physics research planning and reasoning
FrontierPhysics: Evaluating Agents for End-to-End Physics Research
Abstract: AI agents are playing an increasingly important role in physics research. However, existing physics benchmarks only evaluate fixed questions, isolated sub-tasks, or paper reproduction with given solutions, and rarely check research quality alongside correctness. We introduce FrontierPhysics, an end-to-end benchmark with 56 tasks made by 42 physicists based on their own research, covering nine domains across theoretical, computational, and experimental physics. Each task requires agents to review the literature, develop a research plan, conduct research and experiments, and produce structured outputs and scientific manuscripts. Combining deterministic verifiers with expert-authored rubrics, FrontierPhysics evaluates whether agents' research is correct and publishable. Across 22 models in 26 configurations, no configuration passes more than 46 of its 168 rollouts. Manual review of agent trajectories shows that frontier agents' main weaknesses are insufficiently rigorous reasoning and limited expert intuition, rather than gaps in physics knowledge or execution errors.
Digital twin boosts robot learning with visual rewards in lab tasks
TwinBridge: Digital Twin-Driven Policy and Reward Transfer for Real-World Reinforcement Learning in Laboratory Robotics
Abstract: Online reinforcement learning offers an effective approach to precise laboratory manipulation, yet costly real-world demonstrations and limited access to dense process rewards hinder its practical application. We present TwinBridge, a digital twin-driven framework that supplies policy initialization and dense visual rewards for real-world online learning. We construct digital twins by combining 3D Gaussian splatting with physics simulation. Here, simulator states provide task events and geometric progress under physical prerequisites and ordering constraints, yielding rewards for policy pretraining with simulated demonstrations and reinforcement learning. We distill this supervision into a visual reward model. During real-world interaction, its predictions are combined with execution history to compute dense rewards for human-in-the-loop policy refinement. Across five real-world laboratory tasks, TwinBridge achieves a final mean autonomous success rate of 98% with at most 25 minutes of real-world interaction per task. Experiments show that dense rewards improve interaction efficiency over sparse rewards, and simulation-based policy initialization further accelerates learning.
BioAgent robot learns and adapts to complex lab tasks autonomously
BioAgent: Self-Directed Skill Acquisition and Capability Growth for Long-Horizon Laboratory Protocols
Abstract: Executing an unfamiliar laboratory protocol requires a robot to identify missing capabilities and determine whether each operation remains valid as the experiment progresses. This letter presents BioAgent, an embodied agent that addresses these coupled challenges of capability sufficiency and experimental validity. It matches human-reviewed requirements to validated skills and task packages, selects tool-based implementations for missing behaviors, and requests human teaching when needed during learning. Learned skills undergo sequential task-package validation to check outcomes and compatibility between successive operations. During execution, precondition, outcome, and experimental-state checks govern progression, autonomous recovery, or termination. Execution evidence guides tool selection, while accepted experience supports offline policy updates and task packaging. On the second task, BioAgent reuses 17 skill types unchanged, revises two existing implementations, and acquires five new types. On two dual-arm laboratory tasks with 20 and 31 ordered skill invocations, BioAgent achieves complete-task success rates of 66\% and 58\% with autonomous recovery over 50 runs per task. Across 25 atomic skills evaluated over 50 autonomous trials each with recovery disabled, success rates range from 84\% to 100\%, with 17 skills achieving 50/50.
VerifiedLab transforms scientific papers into trusted AI research tools
VerifiedLab: Harnessing Knowns for Unknowns
Abstract: Across human history, knowledge has undergone several transitions, from orality to writing and then to digital archives. At each transition, humans established new conventions to preserve knowledge for the new era. Nowadays, as research agents are increasingly deployed for laboratory experiments, knowledge is crossing another boundary: from records written for humans to those for machines. In this work, we introduce VerifiedLab, a multi-agent harness framework for this human-to-machine transition of knowledge. VerifiedLab transforms research output from passive artifacts into active systems that accelerate downstream use, adoption and prediction of future trends. In VerifiedLab, a team of AI scientists with distinct roles reasons over records verified field by field: a principal investigator plans, a librarian computes the evidence directly from the records, specialists draft, and a gate and a critic check each claim against the measured reliability of its data before the harness decides whether to release or withhold it. We demonstrate the efficacy of VerifiedLab through extensive experiments on perovskite solar cells: VerifiedLab recovers known physical trends, anticipates devices reported a year later, and lets AI scientists inherit the literature together with a measure of how far it can be trusted. By scaling the inference-time verification compute, VerifiedLab introduces a new pathway for knowledge dissemination and machine harness for AI co-scientists.
Machine learning and large language models extract materials data from science texts
Automated Materials Data and Knowledge Extraction using Machine Learning and Large Language Models
Abstract: Over the past decade, substantial efforts have been devoted to developing machine learning (ML) methods for extracting materials data and, where possible, materials knowledge directly from the scientific literature. This review traces the evolution of these methods from heuristic, rule-based pipelines through natural language processing (NLP) models and transformer-based encoders to, lastly, large language models (LLMs) and agentic systems capable of extracting materials information across multiple modalities, including text, tables, and figures. Beside construction of large, queryable materials databases and knowledge graphs that support downstream materials discovery, we discuss how these advances have enabled new capabilities, such as, generic question answering across materials science, AI co-scientists and chatbots for research assistance, and closed-loop optimization and discovery when integrated with autonomous laboratories. We critically assess the datasets generated using these approaches, their extraction accuracy and computational costs, and the respective strengths and limitations of different methodologies, and even provide practical guidelines for developing more reliable and scalable materials data extraction pipelines. Finally, we identify key open challenges, including the extraction of full materials structure-property-processing-performance tetrahedron at the sample level, the scarcity of reliable benchmark datasets for systematic evaluation, and the resolution of non-standard materials terminology across different document modalities.
Feedback does not always improve voltage clamp experiment control
When Does Feedback Help? Auditing Learned Voltage-Clamp Experimental Design
Abstract: A learned scientific controller can outperform a misspecified planner without benefiting from feedback. We audit two synthetic voltage-clamp tasks with a training-selected fixed protocol, current masking, a Bayesian reference, and an excluded target. Five recurrent policies repeat one fixed protocol in all 1,200 off-grid rollouts; masking current changes no decision. In a crossed four-hypothesis task, a fixed diagnostic pulse is followed by one learned choice. Policies then use the first current, but tie a correctly specified Bayesian controller, and a fitted threshold reproduces the learned actions without being that controller. The excluded-target prediction gain is $4.6991\times10^{-6}$ nats per sample. Feedback use and protocol quality are separate tests. These cases establish neither biological discovery nor general RL superiority.
BioPRM improves step-by-step checks of biological experiment protocols
BioPRM: Step-Level Consistency Verification of Biological Protocols
Abstract: Process reward models (PRMs) provide fine-grained supervision for assessing intermediate steps in language-model outputs, but their application to biological protocols presents distinct challenges. Protocol validity depends on both the appropriateness of individual operations and their consistency with the experimental objective and surrounding procedure, while experimental outcomes are typically unavailable during verification. We introduce BioPRM, a contextual process reward model for identifying procedural inconsistencies in structured biological protocols. We construct a supervision corpus from SciRecipe and protocols collected from protocols.io and Bio-protocol using LLM-assisted construction and source-specific review by personnel with biological expertise.
Ai agents tested for efficient scientific experiment planning under budget
Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery
Abstract: AI agents for autonomous scientific discovery must decide which experiments to run under a limited budget. Most benchmarks for science agents provide fixed datasets, while others that support active experimentation largely rely on simulation. We introduce Autonomous Science Bench, an initial release comprising six budgeted design-build-test-learn campaigns grounded in published experiments across biology, chemistry, and materials science. Agents select batches of designs, receive measurements from a lab service, and use the results to guide subsequent experiments before delivering a predictive model. Success requires passing two calibrated gates: a discovery gate, which evaluates the designs the agent measured, and a learning gate, which evaluates its model's ranking of held-out designs. In a pilot evaluation of eight agent-model configurations and 144 trials, the best configuration succeeds in 67% of trials, while the hardest campaign is solved in only three of 24 attempts. The two gates reveal different weaknesses: some agents build accurate rankings but find too few promising designs, while others find promising designs but fail to predict which unseen designs will perform well. These differences are obscured by overall success rates alone. We release version 0.1 of the campaigns, lab runtime, and public leaderboard at https://yibow.me/autonomous-science-bench.
Using longer wavelengths improves protein crystal detection accuracy
Protein Crystallization Segmentation and Classification Using Subordinate Color Channel in Fluorescence Microscopy Images
Abstract: The accuracy of detecting protein crystals for fluorescence microscopy images is very critical for high throughput and automated systems. Although the trace fluorescent labeling method could highlight protein crystals, reflection and emission from the fluorescence dye is not always due to crystal regions. Therefore, the analysis of the peak wavelength in the emission spectra of a fluorophore may not always yield effective results. In this paper, we show that using the subordinate color intensity corresponding to longer wavelengths than the peak wavelength of the emission spectra could improve the accuracy of protein crystal detection. Hence, we have built a segmentation method based on the percentile intensity of the subordinate color for trace fluorescently labeled (TFL'd) protein crystallization trial images. Compared to using the dominant color channel, our segmentation method on subordinate color channel was able to reduce the misclassification rate of likely-leads or crystals as non-crystals by the percentage of from 9.71% to 2.02% depending on the classifier. Similarly, the accuracy of classifiers were increased by the percentage of from 1.77% to 5.53%. Our method reached around 94% accuracy while keeping misclassification of likely-leads and crystals as non-crystals below 1%. Moreover, to evaluate the generalizability of our method, we have conducted new wet lab experiments on two proteins, Concanavalin A (Con A) and Ab inorganic pyrophosphate (AbIPPase), and the misclassification rate was below 1%. Our experiments show that using the subordinate channel may be more helpful for TFL'd protein trial image classification.
Arpes database framework aims to boost ai use in materials research
Framework for an AI-Ready ARPES Community Database
Abstract: Condensed matter stands to gain profoundly from widespread adoption of artificial intelligence (AI). However, its current means of data organization impedes this endeavor. As a premier measure of electronic structure underlying material properties, Angle-Resolved Photoemission Spectroscopy (ARPES) has accumulated over four decades of spectra, yet the community's publication-centered workflow preserves only a highly selected fraction of its experimental record. A shared data ecosystem could transform these fragmented measurements and their contexts into a persistent, collective scientific memory, creating immediate value for reproducibility and reuse while laying the foundation for AI-enabled discovery. In this Perspective, we report outcomes of a recent community workshop and propose a practical path toward such an ecosystem. Its benefits unfold along three timescales. In the near term, standardized, searchable, and citable datasets strengthen analysis pipelines independently of AI. In the intermediate future, community-validated tools operating across laboratories could enable broader reuse and increasingly closed-loop automated experiments. In the long term, a diverse corpus of measured electronic spectra could support foundation models for quantum matter. Looking forward, a diverse corpus of measured electronic spectra could support foundation models for quantum matter and new discoveries. We discuss lessons from existing scientific databases, the current state of AI in ARPES, as well as areas of community convergence on data organization, access, credit, governance, and a staged pilot program.
AI agent swarms make steady progress in scientific research tasks
AI Agent Swarms as Researchers: Progress, Challenges, and Open Questions
Abstract: Artificial intelligence (AI) agents, language models connected to tools and run in a loop, can now carry out long, multi-step tasks with little supervision. We gave swarms of off-the-shelf coding agents a short statement of scope, from a narrow topic to a whole field, access to the literature and to computing tools, and one standing instruction: make real, correct, useful progress, and do not stop. We supplied no scientific ideas. Within weeks, the agents produced a large body of research notes, paper-length drafts, and formal proofs in five areas of optimization theory and physical science, and proposed untested laboratory experiments in a sixth. We do not claim that all of it is correct or new, but it is not noise: in what we have checked so far, we found no major scientific error, and several results are proved in a proof assistant. The agents produced results faster than we could review them; we estimate that a full review would take us months. Together with two widely discussed 2026 results in mathematics obtained with swarms, our runs suggest that agents can already do a large part of routine theoretical research, at least in areas that we experimented with. This raises questions we cannot yet answer: how to trust results when review, not production, is the scarce resource; what credit and publication counts mean when the human input is a prompt, and why institutions would pay researchers rather than buy computing time; and how people can learn a field, add to what agents do, and stay in control of research they cannot keep up with. Research institutions are not ready: models improve faster than institutions change, so they should decide now how to respond as capabilities increase. We offer tentative positions, release the agents' unedited output as of 25 September 2026, and invite readers to repeat the experiment in their own fields.
Active learning framework streamlines scientific data collection for discovery
ALF: An Active Learning Framework for Scientific Discovery
Abstract: Machine learning for scientific discovery is almost systematically data bound. Producing relevant high quality data, under budget constraints, is amongst the most promising ways to advance the field. Active learning (AL) offers promise wherever labelling requires expensive experiment, measurement, or simulation. Most existing tools cover only part of the data acquisition loop, and typically focus on either offline benchmarking or online deployment, but not both. We present ALF, a modular AL Framework that runs the full data acquisition loop via five modular components. One clear API for both settings: offline, against an existing dataset for controlled and reproducible experimentation; and online, against an oracle for acquiring new candidates in real-world deployments. ALF is open-source and available at https://github.com/instadeepai/alf.