Autonomous Experimentation

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

167 papers25 papers in the last four weeks, down 4% on the four weeks before. 0.2% of all new papers.

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/.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Aug 19, 2025

Closing the empirical loop: autonomous AI agents conduct end-to-end research with human participants

Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, yet remain confined to narrow domains requiring substantial human oversight. Exponential growth of scientific literature and increasing domain specialisation constrain researchers capacity to synthesise knowledge across disciplines and develop unifying theories, motivating exploration of more general-purpose AI systems for science. Here we show that a domain-agnostic, agentic AI system can independently navigate the scientific workflow, from hypothesis generation through data collection to manuscript preparation. The system autonomously designed and executed three psychological studies on visual working memory, mental rotation, and imagery vividness, executed online data collection with 288 participants, developed analysis pipelines through over 8-hour continuous coding sessions, and produced completed manuscripts. The results demonstrate the capability of AI scientific discovery pipelines to conduct research with theoretical reasoning and methodological rigour comparable to experienced researchers, though with limitations in conceptual nuance and theoretical interpretation. This is a step toward embodied AI that can test hypotheses through real-world experiments, accelerating discovery by autonomously exploring regions of scientific space that human cognitive and resource constraints might otherwise leave unexplored. It raises important questions about the nature of scientific understanding and attribution of scientific credit.