Autonomous Experimentation

Ask about this topic

Overview

Autonomous experimentation studies how to close the loop between proposing a question, choosing an experiment, collecting results, and using them to guide the next step, in both physical laboratories and computational research. Common approaches include Bayesian optimization and active learning for selecting measurements, reinforcement learning and evolutionary search for control, and language-model agents that plan protocols and coordinate instruments or code. These methods can make costly or slow settings—such as materials synthesis, microscopy, chemistry, and machine-learning model development—more systematic and efficient. Real-world demonstrations are growing, but reliable execution, safety, evidence validation, and sustained improvement remain difficult; benchmarks increasingly test complete experimental trajectories rather than plans or final scores alone.

Latest papers

CardsList

148 papers26 papers in the last four weeks, up 86% on the four weeks before. 0.2% of all new papers.

Apr 29, 2026

Accelerating battery research with an interoperable interface between FINALES and Kadi4Mat

This study investigates how automated and interoperable research infrastructures can accelerate experimental materials research, using battery formation as a case study. We introduce a methodological framework that integrates the FINALES and Kadi Research Data Management ecosystems, enabling coordinated experiment execution, data management, and analysis across distributed research infrastructures. The FINALES framework orchestrates experiment planning and execution on the POLiS Materials Acceleration Platform, while Kadi handles data management, visualization, experiment selection, and persistent storage. This interoperability enables reproducible, coordinated, end-to-end experimental workflows that connect automated systems and human-operated processes across multiple research sites. To showcase the framework's capabilities, we investigate the formation process of sodium-ion coin cells, a critical step that influences cell lifetime. Using a dataset generated through the proposed infrastructure, we analyze the relationships between formation parameters and electrochemical performance. A Gaussian process model is employed to identify regions associated with favorable performance within the investigated parameter domain while quantifying predictive uncertainty, highlighting where additional experimental evidence would be most informative. The presented workflow demonstrates that interoperable, automated infrastructures can support experimental campaigns, enhance data consistency and traceability, and support reproducible, data-driven analysis. While demonstrated through a battery application, the framework provides a general methodology for integrating distributed experimental platforms with RDM systems, transferable across materials science and engineering domains.

Giovanna Tosato (Karlsruhe Institute of Technology), Leon Merker (Karlsruhe Institute of Technology, Helmholtz Institute Ulm +4

Institute for Applied Materials - Microstructure Modeling and Simulation (IAM-MMS), Karlsruhe Institute of Technology (KIT), Germany · Helmholtz Institute Ulm (HIU), Karlsruhe Institute of Technology (KIT), Germany · TUM School of Natural Sciences, Department of Chemistry, Chair of Digital Catalysis, Munich +6

Materials ScienceScientific Workflow AutomationAutonomous Experimentation
AskPDF
Apr 28, 2026

Automated Adversarial Collaboration for Advancing Theory Building in the Cognitive Sciences

Cognitive science often evaluates theories through narrow paradigms and local model comparisons, limiting the integration of evidence across tasks and realizations. We introduce an automated adversarial collaboration framework for adjudicating among competing theories even when the candidate models and experiments must be discovered during the adjudication process. The system combines LLM-based theory agents, program synthesis, and information-theoretic experimental design in a closed loop. In a simulation study spanning three classic categorization theories, the framework recovered the ground-truth theory across noise settings with weaker reliability in the hardest settings. Together, the framework and findings provide a concrete proof of concept for closed-loop, in-silico theory adjudication in cognitive science.

Suyog Chandramouli, George Kachergis, Akshay Jagadish

Department of Psychology, Princeton University · Department of Psychology, Stanford University · Princeton AI Lab, Princeton University

Multi-Agent LLM SystemsComputational Cognitive ModelingAutonomous Experimentation
AskPDF
Apr 26, 2026

Accelerating Quantum Materials Characterization: Hybrid Active Learning for Autonomous Spin Wave Spectroscopy

Autonomous neutron spectroscopy must solve three distinct tasks: detection (where is the signal?), inference (which Hamiltonian governs it?), and refinement (what are the parameters?). No single controller solves all three equally well. We present TAS-AI, a hybrid agnostic-to-physics-informed framework for autonomous triple-axis spin-wave spectroscopy that separates these tasks explicitly. In blind reconstruction benchmarks, model-agnostic methods such as random sampling, coarse grids, and Gaussian-process mappers reach a global error threshold more reliably and with fewer measurements than physics-informed planning, supporting the claim that discovery and inference are distinct tasks requiring distinct controllers. Once signal structure is localized, the physics-informed stage performs in-loop Hamiltonian discrimination and parameter refinement: in a controlled square-lattice test between nearest-neighbor-only and J1-J2 Hamiltonians, TAS-AI reaches a decisive AIC-derived evidence ratio (>100) in fewer than 10 measurements, while motion-aware scheduling cuts wall-clock time by 32% at a fixed measurement budget. We also identify a failure mode of posterior-weighted design, algorithmic myopia, in which the planner over-refines the current leading model while under-sampling low-intensity falsification probes. A constrained falsification channel sharply reduces time spent committed to the wrong model and accelerates correct model selection without modifying the Bayesian inference engine. In controlled two-model ablations, both a deterministic top-two max-disagreement rule and an LLM-based audit committee achieve this gain under identical constraints. We demonstrate the full workflow in silico using a high-fidelity digital twin and provide an open-source Python implementation.

William Ratcliff

NIST Center for Neutron Research, National Institute of Standards and Technology, Gaithersburg, MD 20899, USA

Active LearningMaterials ScienceBayesian Experimental DesignAutonomous Experimentation
AskPDF
Apr 22, 2026

Autonomous Reliability Qualification of Ga2_2O3_3-based Hydrogen and Temperature Sensors via Safe Active Learning

We present a Safe Active Learning (SAL) framework for autonomous reliability characterization of rectifying Ga2_2O3_3-based devices under coupled thermal and hydrogen stress. SAL treats rectification as a device-physics-motivated safety observable and models its evolution over elapsed time, temperature, and H2_2 concentration using a Gaussian-process surrogate. To handle condition-dependent and uncertain experiment durations, the method combines an adaptive completion-time window, time-window lower-confidence-bound safety checks, a trust region anchored to previously verified safe conditions, and a two-phase strategy that transitions from conservative safe exploration to progressively relaxed rectification targets as the device degrades. We first evaluate SAL in simulation, where it safely expands the explored region while learning the evolving rectification surface. We then demonstrate SAL experimentally on an automated high-temperature probe-station platform using a Pt/Cr2_2O3_3:Mg/ββ-Ga2_2O3_3 device. In the reported campaign, phase 1 incurred only one unsafe measurement associated with spurious current-voltage sweeps, while phase 2 intentionally probed lower-rectification regimes. Finally, we use the curated SAL dataset for offline long-horizon forecasting of device response at a target voltage using a structured Gaussian-process model with a condition-dependent Kohlrausch--Williams--Watts mean and a residual covariance kernel. The model captures long-time, saturating degradation trends in an auxiliary validation dataset, illustrating how safety-aware autonomous experimentation enables both conservative characterization and subsequent degradation modeling. Although demonstrated here for a rectifying Ga2_2O3_3 device, SAL is applicable to other systems where a measurable in situ safety observable can be defined.

Davi Febba, William A. Callahan, Anna Sacchi +1

Materials Science Center, National Laboratory of the Rockies (NLR), Golden, CO 80401, USA

Active LearningAutonomous Experimentation
AskPDF
Apr 15, 2026

MIND: AI Co-Scientist for Material Research

Large language models (LLMs) have enabled agentic AI systems for scientific discovery, but most approaches remain limited to textbased reasoning without automated experimental verification. We propose MIND, an LLM-driven framework for automated hypothesis validation in materials research. MIND organizes the scientific discovery process into hypothesis refinement, experimentation, and debate-based validation within a multi-agent pipeline. For experimental verification, the system integrates Machine Learning Interatomic Potentials, particularly SevenNet-Omni, enabling scalable in-silico experiments. We also provide a web-based user interface for automated hypothesis testing. The modular design allows additional experimental modules to be integrated, making the framework adaptable to broader scientific workflows. The code is available at: https://github.com/IMMS-Ewha/MIND, and a demonstration video at: https://youtu.be/lqiFe1OQzN4.

Geonhee Ahn, Donghyun Lee, Hayoung Doo +3

Institute for Multiscale Matter and Systems (IMMS), Ewha Womans University, Seoul 03760, Republic of Korea

AI Agents for Scientific DiscoveryAutonomous ExperimentationMaterials ScienceMulti-Agent LLM Systems
AskPDF
Apr 13, 2026

Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors

Self-driving laboratories promise to accelerate materials discovery. Yet current automated solid-state synthesis platforms are limited to ambient conditions, thereby precluding their use for air-sensitive materials. Here, we present A-Lab for Glovebox Powder Solid-state Synthesis (A-Lab GPSS), a robotic platform capable of synthesizing and characterizing air-sensitive inorganic materials under strict air-free conditions. By integrating an agentic AI framework into the A-Lab GPSS platform, we structure autonomous experimental design through abductive and inductive reasoning. We deploy this platform to explore the vast compositional space of lithium halide spinel solid-state ionic conductors. Across a synthesis campaign comprising 352 samples with diverse compositions, the system explores a broad chemical space, experimentally realizing 72% of the 171 possible pairwise combinations among the 19 metals considered in this study. Over the course of the campaign, the fraction of compositions exhibiting both good ionic conductivity (> 0.05 mS/cm) and high halide spinel phase purity increases from 1.33% in the first 75 agent-proposed samples to 5.33% in the final 75. Furthermore, by inspecting the AI's reasoning processes, we reveal distinct yet complementary discovery strategies: abductive reasoning interrogates abnormal observations within already explored regions, whereas inductive reasoning expands the search into broader, previously unvisited chemical space. This work establishes a scalable platform for the autonomous discovery of complex, air-sensitive solid-state materials.

Yuxing Fei, Bernardus Rendy, Xiaochen Yang +7

Department of Materials Science & Engineering, University of California, Berkeley, Berkeley, California 94720, United States · Materials Sciences Division, Lawrence Berkeley National Laboratory, Berkeley, California 94720, United States · Energy Storage Research Alliance, Argonne National Laboratory, Lemont, Illinois 60439, United States +2

Autonomous ExperimentationLaboratory AutomationMaterials ScienceLarge Language Model-Guided Scientific Discovery
AskPDF
Apr 13, 2026

Autonomous Diffractometry Enabled by Visual Reinforcement Learning

Automation underpins progress across scientific and industrial disciplines. Yet, automating tasks requiring interpretation of abstract visual information remain challenging. For example, crystal alignment strongly relies on humans with the ability to comprehend diffraction patterns. Here we introduce an autonomous system that aligns single crystals without access to crystallography and diffraction theory. Using a model-free reinforcement learning framework, an agent learns to identify and navigate towards high-symmetry orientations directly from Laue diffraction patterns. Despite the absence of human supervision, the agent develops human-like strategies to achieve time-efficient alignment across different crystal symmetry classes. With this, we provide a computational framework for intelligent diffractometers. As such, our approach advances the development of automated experimental workflows in materials science.

J. Oppliger, M. Stifter, A. Rüegg +7

Physik-Institut, Universität Zürich, Winterthurerstrasse 190, CH-8057 Zürich, Switzerland · Jeremiah Horrocks Institute for Mathematics, Physics and Astronomy, University of Central Lancashire, Preston PR1 2HE, United Kingdom · Department of Physics, Clarendon Laboratory, University of Oxford, Oxford OX1 RPU, United Kingdom +3

Autonomous ExperimentationLaboratory Automation
AskPDF
Apr 12, 2026

Camyla: Scaling Autonomous Research in Medical Image Segmentation

We present Camyla, a system for fully autonomous research within the scientific domain of medical image segmentation. Camyla transforms raw datasets into literature-grounded research proposals, executable experiments, and complete manuscripts without human intervention. Autonomous experimentation over long horizons poses three interrelated challenges: search effort drifts toward unpromising directions, knowledge from earlier trials degrades as context accumulates, and recovery from failures collapses into repetitive incremental fixes. To address these challenges, the system combines three coupled mechanisms: Quality-Weighted Branch Exploration for allocating effort across competing proposals, Layered Reflective Memory for retaining and compressing cross-trial knowledge at multiple granularities, and Divergent Diagnostic Feedback for diversifying recovery after underperforming trials. The system is evaluated on CamylaBench, a contamination-free benchmark of 31 datasets constructed exclusively from 2025 publications, under a strict zero-intervention protocol across two independent runs within a total of 28 days on an 8-GPU cluster. Across the two runs, Camyla generates more than 2,700 novel model implementations and 40 complete manuscripts, and surpasses the strongest per-dataset baseline selected from 14 established architectures, including nnU-Net, on 22 and 18 of 31 datasets under identical training budgets, respectively (union: 24/31). Senior human reviewers score the generated manuscripts at the T1/T2 boundary of contemporary medical imaging journals. Relative to automated baselines, Camyla outperforms AutoML and NAS systems on aggregate segmentation performance and exceeds six open-ended research agents on both task completion and baseline-surpassing frequency. These results suggest that domain-scale autonomous research is achievable in medical image segmentation.

Yifan Gao, Haoyue Li, Feng Yuan +3

University of Science and Technology of China · Shanghai Innovation Institute · Shanghai Jiao Tong University +1

Autonomous Research AgentsAutonomous ExperimentationMedical Image Segmentation
AskPDF
Apr 7, 2026

Deep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring

We present Deep Researcher Agent, an open-source framework that enables large language model (LLM) agents to autonomously conduct deep learning experiments around the clock. Unlike existing AI research assistants that focus on paper writing or code generation, our system addresses the full experiment lifecycle: hypothesis formation, code implementation, training execution, result analysis, and iterative refinement. The framework introduces three key innovations: (1) Zero-Cost Monitoring -- a monitoring paradigm that incurs zero LLM API costs during model training by relying solely on process-level checks and log file reads; (2) Two-Tier Constant-Size Memory -- a memory architecture capped at ∼\sim5K characters regardless of runtime duration, preventing the unbounded context growth that plagues long-running agents; and (3) Minimal-Toolset Leader-Worker Architecture -- a multi-agent design where each worker agent is equipped with only 3--5 tools, reducing per-call token overhead by up to 73%. In sustained deployments spanning 30+ days, the framework autonomously completed 500+ experiment cycles across four concurrent research projects, achieving a 52% improvement over baseline metrics in one project through 200+ automated experiments -- all at an average LLM cost of $0.08 per 24-hour cycle. Code is available at https://github.com/Xiangyue-Zhang/auto-deep-researcher-24x7.

Xiangyue Zhang

The University of Tokyo

Autonomous Research AgentsAutonomous ExperimentationAI Agent MonitoringMulti-Agent LLMsMemory-Augmented Language Model Agents
AskPDF
Apr 7, 2026

AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery

Artificial intelligence research increasingly depends on prolonged cycles of reproduction, debugging, and iterative refinement to achieve State-Of-The-Art (SOTA) performance, creating a growing need for systems that can accelerate the full pipeline of empirical model optimization. In this work, we introduce AutoSOTA, an end-to-end automated research system that advances the latest SOTA models published in top-tier AI papers to reproducible and empirically improved new SOTA models. We formulate this problem through three tightly coupled stages: resource preparation and goal setting; experiment evaluation; and reflection and ideation. To tackle this problem, AutoSOTA adopts a multi-agent architecture with eight specialized agents that collaboratively ground papers to code and dependencies, initialize and repair execution environments, track long-horizon experiments, generate and schedule optimization ideas, and supervise validity to avoid spurious gains. We evaluate AutoSOTA on recent research papers collected from eight top-tier AI conferences under filters for code availability and execution cost. Across these papers, AutoSOTA achieves strong end-to-end performance in both automated replication and subsequent optimization. Specifically, it successfully discovers 105 new SOTA models that surpass the original reported methods, averaging approximately five hours per paper. Case studies spanning LLM, NLP, computer vision, time series, and optimization further show that the system can move beyond routine hyperparameter tuning to identify architectural innovation, algorithmic redesigns, and workflow-level improvements. These results suggest that end-to-end research automation can serve not only as a performance optimizer, but also as a new form of research infrastructure that reduces repetitive experimental burden and helps redirect human attention toward higher-level scientific creativity.

Yu Li, Chenyang Shao, Xinyang Liu +13

Department of Electronic Engineering, BNRist, Tsinghua University · Zhongguancun Academy · Peking University +1

Autonomous ExperimentationAutonomous Research AgentsAutomated Algorithm DiscoveryAutomated Machine Learning
AskPDF
Apr 5, 2026

PATHFINDER: Multi-objective discovery in structural and spectral spaces

Automated decision-making is becoming key for automated characterization including electron and scanning probe microscopies and nano indentation. Most machine learning driven workflows optimize a single predefined objective and tend to converge prematurely on familiar responses, overlooking rare but scientifically important states. More broadly, the challenge is not only where to measure next, but how to coordinate exploration across structural, spectral, and measurement spaces under finite experimental budgets while balancing target-driven optimization with novelty discovery. Here we introduce PATHFINDER, a framework for autonomous microscopy that combines novelty driven exploration with optimization, helping the system discover more diverse and useful representations across structural, spectral, and measurement spaces. By combining latent space representations of local structure, surrogate modeling of functional response, and Pareto-based acquisition, the framework selects measurements that balance novelty discovery in feature and object space and are informative and experimentally actionable. Benchmarked on pre acquired STEM EELS data and realized experimentally in scanning probe microscopy of ferroelectric materials, this approach expands the accessible structure property landscape and avoids collapse onto a single apparent optimum. These results point to a new mode of autonomous microscopy that is not only optimization-driven, but also discovery-oriented, broad in its search, and responsive to human guidance.

Kamyar Barakati, Boris N. Slautin, Utkarsh Pratiush +2

Department of Materials Science and Engineering, University of Tennessee, Knoxville, TN, USA · Department of Materials Science and Engineering, Institute of Science Tokyo, Yokohama, Japan

Autonomous ExperimentationMulti-Objective OptimizationElectron MicroscopyNovelty Search
AskPDF
Apr 1, 2026

Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial

Traditional scientific discovery relies on an iterative hypothesise-experiment-refine cycle that has driven progress for centuries, but its intuitive, ad-hoc implementation often wastes resources, yields inefficient designs, and misses critical insights. This tutorial presents Bayesian Optimisation (BO), a principled probability-driven framework that formalises and automates this core scientific cycle. BO uses surrogate models (e.g., Gaussian processes) to model empirical observations as evolving hypotheses, and acquisition functions to guide experiment selection, balancing exploitation of known knowledge and exploration of uncharted domains to eliminate guesswork and manual trial-and-error. We first frame scientific discovery as an optimisation problem, then unpack BO's core components, end-to-end workflows, and real-world efficacy via case studies in catalysis, materials science, organic synthesis, and molecule discovery. We also cover critical technical extensions for scientific applications, including batched experimentation, heteroscedasticity, contextual optimisation, and human-in-the-loop integration. Tailored for a broad audience, this tutorial bridges AI advances in BO with practical natural science applications, offering tiered content to empower cross-disciplinary researchers to design more efficient experiments and accelerate principled scientific discovery.

Zhongwei Yu, Rasul Tutunov, Alexandre Max Maraval +13

The Hong Kong University of Science and Technology (Guangzhou) · Huawei Noah’s Ark Lab · University of Science and Technology of China +5

Bayesian OptimizationScientific DiscoveryBayesian Experimental DesignAutonomous Experimentation
AskPDF
Mar 31, 2026

AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs

We present AlphaLab, an autonomous research harness that leverages frontier LLM agentic capabilities to automate the full experimental cycle in quantitative, computation-intensive domains. Given only a dataset and a natural-language objective, AlphaLab proceeds through three phases without human intervention: (1) it adapts to the domain and explores the data, writing analysis code and producing a research report; (2) it constructs and adversarially validates its own evaluation framework; and (3) it runs large-scale GPU experiments via a Strategist/Worker loop, accumulating domain knowledge in a persistent playbook that functions as a form of online prompt optimization. All domain-specific behavior is factored into adapters generated by the model itself, so the same pipeline handles qualitatively different tasks without modification. We evaluate AlphaLab with two frontier LLMs (GPT-5.2 and Claude Opus 4.6) on three domains: CUDA kernel optimization, where it writes GPU kernels that run 4.4x faster than torch.compile on average (up to 91x); LLM pretraining, where the full system achieves 22% lower validation loss than a single-shot baseline using the same model; and traffic forecasting, where it beats standard baselines by 23-25% after researching and implementing published model families from the literature. The two models discover qualitatively different solutions in every domain (neither dominates uniformly), suggesting that multi-model campaigns provide complementary search coverage. We additionally report results on financial time series forecasting in the appendix, and release all code at https://brendanhogan.github.io/alphalab-paper/.

Brendan R. Hogan, Xiwen Chen, James T. Wilson +5

Morgan Stanley

Autonomous Research AgentsAutonomous ExperimentationLarge Language Model-Guided OptimizationAutomated Algorithm DiscoveryMulti-Agent LLMsGPU Kernel Optimization
AskPDF
Mar 31, 2026

Quality-Controlled Active Learning via Gaussian Processes for Robust Structure-Property Learning in Autonomous Microscopy

Autonomous experimental systems are increasingly used in materials research to accelerate scientific discovery, but their performance is often limited by low-quality, noisy data. This issue is especially problematic in data intensive structure-property learning tasks such as Image-to-Spectrum (Im2Spec) and Spectrum-to-Image (Spec2Im) translations, where standard active learning strategies can mistakenly prioritize poor quality measurements. We introduce a gated active learning framework that combines curiosity driven sampling with a physics-informed quality control filter based on Simple Harmonic Oscillator model fits, allowing the system to automatically exclude low fidelity data during acquisition. Evaluations on a pre-acquired dataset of band-excitation piezoresponse spectroscopy (BEPS) data from PbTiO3 thin films with spatially localized noise show that the proposed method outperforms random sampling, standard active learning, and multitask learning strategies. We further deployed the framework in real-time experiments on a separate PbTiO3 thin-film sample with heterogeneous domain structures, demonstrating its effectiveness in autonomous microscopy experiments. Overall, this work supports hybrid autonomy in self-driving labs, where physics-informed quality assessment and active decision making work together for more reliable discovery.

Jawad Chowdhury, Ganesh Narasimha, Jan-Chi Yang +4

Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, TN, 37831, USA. · Department of Physics, National Cheng Kung University, Tainan, 70101, Taiwan.

Active LearningPhysics-Informed MLAutonomous Experimentation
AskPDF
Mar 25, 2026

Toward Full Autonomous Laboratory Instrumentation Control with Large Language Models

The control of complex laboratory instrumentation often requires significant programming expertise, creating a barrier for researchers lacking computational skills. This work explores the potential of large language models (LLMs), such as ChatGPT, and LLM-based artificial intelligence (AI) agents to enable efficient programming and automation of scientific equipment. Through a case study involving the implementation of a setup that can be used as a single-pixel camera or a scanning photocurrent microscope, we demonstrate how ChatGPT can facilitate the creation of custom scripts for instrumentation control, significantly reducing the technical barrier for experimental customization. Building on this capability, we further illustrate how LLM-assisted tools can be extended into autonomous AI agents capable of independently operating laboratory instruments and iteratively refining control strategies. This approach underscores the transformative role of LLM-based tools and AI agents in democratizing laboratory automation and accelerating scientific progress.

Yong Xie, Kexin He, Andres Castellanos-Gomez

Key Laboratory of Wide Band-Gap Semiconductor Technology, School of Advanced Materials and Nanotechnology, Xidian University, Xi’an 710071, China · 2D Foundry Research Group. Instituto de Ciencia de Materiales de Madrid (ICMM-CSIC), Madrid, E-28049, Spain.

Laboratory AutomationAutonomous ExperimentationLanguage Model-Based ControlLLM Agents
AskPDF
Mar 25, 2026

AgentChemist: A Multi-Agent Experimental Robotic Platform Integrating Chemical Perception and Precise Control

Chemical laboratory automation has long been constrained by rigid workflows and poor adaptability to the long-tail distribution of experimental tasks. While most automated platforms perform well on a narrow set of standardized procedures, real laboratories involve diverse, infrequent, and evolving operations that fall outside predefined protocols. This mismatch prevents existing systems from generalizing to novel reaction conditions, uncommon instrument configurations, and unexpected procedural variations. We present a multi-agent robotic platform designed to address this long-tail challenge through collaborative task decomposition, dynamic scheduling, and adaptive control. The system integrates chemical perception for real-time reaction monitoring with feedback-driven execution, enabling it to adjust actions based on evolving experimental states rather than fixed scripts. Validation via acid-base titration demonstrates autonomous progress tracking, adaptive dispensing control, and reliable end-to-end experiment execution. By improving generalization across diverse laboratory scenarios, this platform provides a practical pathway toward intelligent, flexible, and scalable laboratory automation.

Xiangyi Wei, Fei Wang, Haotian Zhang +6

School of Computer Science and Technology, East China Normal University, Shanghai, China. · School of Chemistry and Molecular Engineering, East China Normal University, Shanghai, China. · School of Data Science and Engineering, East China Normal University, Shanghai, China. +1

Laboratory AutomationAutonomous ExperimentationRobotic ControlMulti-Agent Orchestration
AskPDF
Mar 22, 2026

Toward an automated science of the mind

Artificial Intelligence is starting to automate scientific discovery, raising the prospect of an automated science of the mind. We chart this field around four challenges: representing experiments, generating synthetic behavior, synthesizing models, and closing the loop to discover psychological theories.

Akshay K. Jagadish, Milena Rmus, Kristin Witte +3

Princeton AI Lab, Princeton University, New Jersey, USA · Institute for Human-Centered AI, Helmholtz Munich, Neuherberg, Germany · Ludwig-Maximilians-University, Munich, 80539, Germany

Autonomous Scientific DiscoveryScientific DiscoveryAutonomous ExperimentationComputational Cognitive Modeling
AskPDF
Mar 20, 2026

Embodied Science: Closing the Discovery Loop with Agentic Embodied AI

Artificial intelligence has demonstrated remarkable capability in predicting scientific properties, yet scientific discovery remains an inherently physical, long-horizon pursuit governed by experimental cycles. Most current computational approaches are misaligned with this reality, framing discovery as isolated, task-specific predictions rather than continuous interaction with the physical world. Here, we argue for embodied science, a paradigm that reframes scientific discovery as a closed loop tightly coupling agentic reasoning with physical execution. We propose a unified Perception-Language-Action-Discovery (PLAD) framework, wherein embodied agents perceive experimental environments, reason over scientific knowledge, execute physical interventions, and internalize outcomes to drive subsequent exploration. By grounding computational reasoning in robust physical feedback, this approach bridges the gap between digital prediction and empirical validation, offering a roadmap for autonomous discovery systems in the life and chemical sciences.

Xiang Zhuang, Chenyi Zhou, Kehua Feng +10

Zhejiang University, Hangzhou, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · Tongji University, Shanghai, China

AI Agents for Scientific DiscoveryAutonomous ExperimentationEmbodied AIScientific Reasoning in Language Models
AskPDF
Mar 17, 2026

Novelty-Driven Target-Space Discovery in Automated Electron and Scanning Probe Microscopy

Modern automated microscopy faces a fundamental discovery challenge: in many systems, the most important scientific information does not reside in the immediately visible image features, but in the target space of sequentially acquired spectra or functional responses, making it essential to develop strategies that can actively search for new behaviors rather than simply optimize known objectives. Here, we developed a deep-kernel-learning BEACON framework that is explicitly designed to guide discovery in the target space by learning structure-property relationships during the experiment and using that evolving model to seek diverse response regimes. We first established the method through demonstration workflows built on pre-acquired ground-truth datasets, which enabled direct benchmarking against classical acquisition strategies and allowed us to define a set of monitoring functions for comparing exploration quality, target-space coverage, and surrogate-model behavior in a transparent and reproducible manner. This benchmarking framework provides a practical basis for evaluating discovery-driven algorithms, not just optimization performance. We then operationalized and deployed the workflow on STEM, showing that the approach can transition from offline validation to real experimental implementation. To support adoption and extension by the broader community, the associated notebooks are available, allowing users to reproduce the workflows, test the benchmarks, and adapt the method to their own instruments and datasets.

Utkarsh Pratiush, Kamyar Barakati, Boris N. Slautin +4

Department of Materials Science and Engineering, University of Tennessee, Knoxville, TN 37996, USA · Department of Chemistry, University of Washington, Seattle, WA 98195, USA · Pacific Northwest National Laboratory, Richland, WA 99354, USA

Deep Kernel LearningScanning Transmission Electron MicroscopyAutonomous ExperimentationElectron MicroscopyMicroscopy Image Analysis
AskPDF
Mar 17, 2026

Toward Experimentation-as-a-Service in 5G/6G: The Plaza6G Prototype for AI-Assisted Trials

This paper presents Plaza6G, the first operational Experiment-as-a-Service (ExaS) platform unifying cloud resources with next-generation wireless infrastructure. Developed at CTTC in Barcelona, Plaza6G integrates GPU-accelerated compute clusters, multiple 5G cores, both open-source (e.g., Free5GC) and commercial (e.g., Cumucore), programmable RANs, and physical or emulated user equipment under unified orchestration. In Plaza6G, the experiment design requires minimal expertise as it is expressed in natural language via a web portal or a REST API. The web portal and REST API are enhanced with a Large Language Model (LLM)-based assistant, which employs retrieval-augmented generation (RAG) for up-to-date experiment knowledge and Low-Rank Adaptation (LoRA) for continuous domain fine-tuning. Over-the-air (OTA) trials leverage a four-chamber anechoic facility and a dual-site outdoor 5G network operating in sub-6~GHz and mmWave bands. Demonstrations include automated CI/CD integration with sub-ten-minute setup and interactive OTA testing under programmable propagation conditions. Machine-readable experiment descriptors ensure reproducibility, while future work targets policy-aware orchestration, safety validation, and federated testbed integration toward open, reproducible wireless experimentation.

Sergio Barrachina-Muñoz, Marc Carrascosa-Zamacois, Horacio Bleda +6

Centre Tecnològic de Telecomunicacions de Catalunya (CTTC/CERCA), Barcelona, Spain

Autonomous ExperimentationWireless Communications6G Networks
AskPDF
Mar 16, 2026

Auto Researching, not hyperparameter tuning: Convergence Analysis of 10,000 Experiments

When LLM agents autonomously design ML experiments, do they perform genuine architecture search -- or do they default to hyperparameter tuning within a narrow region of the design space? We answer this question by analyzing 10,469 experiments executed by two LLM agents (Claude Opus and Gemini 2.5 Pro) across a combinatorial configuration space of 108,000 discrete cells for dashcam collision detection over 27 days. Through ANOVA decomposition, we find that architectural choices explain 94% of performance variance (F=1324F = 1324, η2=0.94η^2 = 0.94), while hyperparameter variation within a fixed architecture explains only 6%. Cross-task validation on a second collision dataset confirms this finding (75% architecture-explained variance) with a different winning backbone, confirming genuine architecture discovery. The agents' key contribution is discovering that V-JEPA,2 video features with Zipformer temporal encoders achieve 0.9245 AP -- a configuration no human proposed -- and concentrating search on productive architectural regions: at N=50N = 50, LLM-guided search reaches AP =0.985= 0.985 versus 0.9650.965 for from-scratch random search. Post-bugfix convergence follows a power law (c=0.11c = 0.11, R2=0.93R^2 = 0.93); the low exponent reflects the cost of broad exploration, not inefficiency, since the LLM discovers qualitatively better regions than random or Bayesian baselines. We characterize multi-agent search dynamics via entropy cycles and Jensen--Shannon specialization, providing the first large-scale empirical framework for LLM-guided combinatorial ML experiment design.

Xiaoyi Li

Large Language Model-Guided NASAutonomous ExperimentationNeural Architecture Search
AskPDF
Mar 13, 2026

Human-AI Collaborative Autonomous Experimentation With Proxy Modeling for Comparative Observation

Optimization for different tasks like material characterization, synthesis, and functional properties for desired applications over multi-dimensional control parameters need a rapid strategic search through active learning such as Bayesian optimization (BO). However, such high-dimensional experimental physical descriptors are complex and noisy, from which realization of a low-dimensional mathematical scalar metrics or objective functions can be erroneous. Moreover, in traditional purely data-driven autonomous exploration, such objective functions often ignore the subtle variation and key features of the physical descriptors, thereby can fail to discover unknown phenomenon of the material systems. To address this, here we present a proxy-modelled Bayesian optimization (px-BO) via on-the-fly teaming between human and AI agents. Over the loop of BO, instead of defining a mathematical objective function directly from the experimental data, we introduce a voting system on the fly where the new experimental outcome will be compared with existing experiments, and the human agents will choose the preferred samples. These human-guided comparisons are then transformed into a proxy-based objective function via fitting Bradley-Terry (BT) model. Then, to minimize human interaction, this iteratively trained proxy model also acts as an AI agent for future surrogate human votes. Finally, these surrogate votes are periodically validated by human agents, and the corrections are then learned by the proxy model on-the-fly. We demonstrated the performance of the proposed px-BO framework into simulated and BEPS data generated from PTO sample. We find that our approach provided better control of the domain experts for an improved search over traditional data-driven exploration, thus, signifies the importance of human-AI teaming in an accelerated and meaningful material space exploration.

Arpan Biswas, Hiroshi Funakubo, Yongtao Liu

University of Tennessee-Oak Ridge Innovation Institute, University of Tennessee, Knoxville, TN 37996, USA · Department of Material Science and Engineering, Institute of Science Tokyo, Yokohama, 226-8502, Japan · Center for Nanophase Materials Sciences, Oak Ridge National Laboratory, Oak Ridge, TN 37830, USA

Autonomous ExperimentationBayesian OptimizationHuman-in-the-Loop AIMaterials ScienceHuman Preference Modeling
AskPDF
Mar 9, 2026

Large Language Model-Assisted Superconducting Qubit Experiments

Superconducting circuits have demonstrated significant potential in quantum information processing and quantum sensing. Implementing novel control and measurement sequences for superconducting qubits is often a complex and time-consuming process, requiring extensive expertise in both the underlying physics and the specific hardware and software. In this work, we introduce a framework that leverages a large language model (LLM) to automate qubit control and measurement. Specifically, our framework conducts experiments by generating and invoking schema-less tools on demand via a knowledge base on instrumental usage and experimental procedures. We showcase this framework with two experiments: an autonomous resonator characterization and a direct reproduction of a quantum non-demolition (QND) characterization of a superconducting qubit from literature. This framework enables rapid deployment of standard control-and-measurement protocols and facilitates implementation of novel experimental procedures, offering a more flexible and user-friendly paradigm for controlling complex quantum hardware.

Shiheng Li, Jacob M. Miller, Phoebe J. Lee +14

Department of Physics, University of Chicago, Chicago, IL 60637, USA · Pritzker School of Molecular Engineering, University of Chicago, Chicago, IL 60637, USA · Pico group, QTF Centre of Excellence, Department of Applied Physics, Aalto University School of Science, P.O. Box 13500, 00076 Aalto, Finland +2

Autonomous ExperimentationLanguage Model-Based ControlLLM Tool Use
AskPDF
Mar 7, 2026

AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery

We present AutoResearch-RL, a framework in which a reinforcement learning agent conducts open-ended neural architecture and hyperparameter research without human supervision, running perpetually until a termination oracle signals convergence or resource exhaustion. At each step the agent proposes a code modification to a target training script, executes it under a fixed wall clock time budget, observes a scalar reward derived from validation bits-per-byte (val-bpb), and updates its policy via Proximal Policy Optimisation (PPO). The key design insight is the separation of three concerns: (i) a frozen environment (data pipeline, evaluation protocol, and constants) that guarantees fair cross-experiment comparison; (ii) a mutable target file (train.py) that represents the agent's editable state; and (iii) a meta-learner (the RL agent itself) that accumulates a growing trajectory of experiment outcomes and uses them to inform subsequent proposals. We formalise this as a Markov Decision Process, derive convergence guarantees under mild assumptions, and demonstrate empirically on a single GPU nanochat pretraining benchmark that AutoResearch-RL discovers configurations that match or exceed hand-tuned baselines after approximately 300 overnight iterations, with no human in the loop.

Nilesh Jain, Rohit Yadav, Sagar Kotian +1

Yale · Google Cloud · Stanford +5

Autonomous Research AgentsAutonomous ExperimentationNeural Architecture SearchHyperparameter Optimization
AskPDF
Mar 1, 2026

BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

Large language models (LLMs) have demonstrated significant reasoning capabilities in scientific discovery but struggle to bridge the gap to physical execution in wet-labs. In these irreversible environments, probabilistic hallucinations are not merely incorrect; they can cause equipment damage or experimental failure. We propose BioProAgent, a neuro-symbolic framework that anchors probabilistic planning in a deterministic Finite State Machine (FSM). We introduce a State-Augmented Planning mechanism that enforces a rigorous Design-Verify-Rectify workflow, ensuring hardware compliance before execution. Furthermore, we address the context bottleneck inherent in complex device schemas by Semantic Symbol Grounding, reducing token consumption by ~6* through symbolic abstraction. In the extended BioProBench benchmark, BioProAgent achieves 95.6% physical compliance (compared to 21.0% for ReAct), demonstrating that neuro-symbolic constraints are essential for reliable autonomy in irreversible physical environments. Code: https://github.com/YuyangSunshine/bioproagent | Website: https://yuyangsunshine.github.io/BioPro-Project.

Yuyang Liu, Jingya Wang, Liuzhenghao Lv +1

School of AI for Science, Peking University · School of Electronic and Computer Engineering, Peking University · School of Computer Science, Peking University

Autonomous ExperimentationNeuro-Symbolic PlanningLaboratory AutomationSymbolic PlanningNeuro-Symbolic ReasoningAI Agent Safety Benchmarks
AskPDF
Feb 24, 2026

A Robotic Testing Platform for Pipelined Discovery of Resilient Soft Actuators

Short lifetime under high electrical fields hinders the widespread robotic application of linear dielectric elastomer actuators (DEAs). Systematic scanning is difficult due to time-consuming per-sample testing and the high-dimensional parameter space affecting performance. To address this, we propose an optimization pipeline enabled by a novel testing robot capable of scanning DEA lifetime. The robot integrates electro-mechanical property measurement, programmable voltage input, and multi-channel testing capacity. Using it, we scanned the lifetime of Elastosil-based linear actuators across parameters including input voltage magnitude, frequency, electrode material concentration, and electrical connection filler. The optimal parameter combinations improved operational lifetime under boundary operating conditions by up to 100% and were subsequently scaled up to achieve higher force and displacement output. The final product demonstrated resilience on a modular, scalable quadruped walking robot with payload carrying capacity (>100% of its untethered body weight, and >700% of combined actuator weight). This work is the first to introduce a self-driving lab approach into robotic actuator design.

Ang Li, Alexander Yin, Alexander White +6

Department of Mechanical and Industrial Engineering, University of Toronto, Toronto, ON, M5S 3G8 Canada · Institute of Materials Science, University of Connecticut, Storrs, CT, 06269 U.S.A. · School of Mechanical, Aerospace, and Manufacturing Engineering, University of Connecticut, Storrs, CT, 06269 U.S.A. +2

Soft RoboticsAutonomous ExperimentationRobotic Data Collection
AskPDF
Feb 19, 2026

Toward a Fully Autonomous, AI-Native Particle Accelerator

This position paper presents a vision for self-driving particle accelerators that operate autonomously with minimal human intervention. We propose that future facilities be designed through artificial intelligence (AI) co-design, where AI jointly optimizes the accelerator lattice, diagnostics, and science application from inception to maximize performance while enabling autonomous operation. Rather than retrofitting AI onto human-centric systems, we envision facilities designed from the ground up as AI-native platforms. We outline nine critical research thrusts spanning agentic control architectures, knowledge integration, adaptive learning, digital twins, health monitoring, safety frameworks, modular hardware design, multimodal data fusion, and cross-domain collaboration. This roadmap aims to guide the accelerator community toward a future where AI-driven design and operation deliver unprecedented science output and reliability.

Chris Tennant

Jefferson Laboratory 12000 Jefferson Ave Newport News, VA 23606

AI ControlAutonomous Experimentation
AskPDF
Sep 21, 2025

Agentic Artificial Intelligence for Multistage Physics Experiments at a Large-Scale User Facility Particle Accelerator

We present the first language-model-driven agentic artificial intelligence (AI) system to autonomously execute multi-stage physics experiments on a production synchrotron light source. Implemented at the Advanced Light Source particle accelerator, the system translates natural language user prompts into structured execution plans that combine archive data retrieval, control-system channel resolution, automated script generation, controlled machine interaction, and analysis. In a representative machine physics task, we show that preparation time was reduced by two orders of magnitude relative to manual scripting even for a system expert, while operator-standard safety constraints were strictly upheld. Core architectural features, plan-first orchestration, bounded tool access, and dynamic capability selection, enable transparent, auditable execution with fully reproducible artifacts. These results establish a blueprint for the safe integration of agentic AI into accelerator experiments and demanding machine physics studies, as well as routine operations, with direct portability across accelerators worldwide and, more broadly, to other large-scale scientific infrastructures.

Thorsten Hellert, Drew Bertwistle, Simon C. Leemann +2

Lawrence Berkeley National Laboratory, Berkeley, California 94720, USA

AI for ScienceAgentic WorkflowsAutonomous Experimentation
AskPDF