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

CardsList

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

  1. Accelerating battery research with an interoperable interface between FINALES and Kadi4Mat

    Apr 29, 2026Giovanna Tosato (Karlsruhe Institute of Technology), Leon Merker (Karlsruhe Institute of Technology, Helmholtz Institute Ulm +4Materials ScienceScientific Workflow Automation

  2. Automated Adversarial Collaboration for Advancing Theory Building in the Cognitive Sciences

    Apr 28, 2026Suyog Chandramouli, George Kachergis, Akshay JagadishMulti-Agent LLM SystemsComputational Cognitive Modeling

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

    Apr 26, 2026William RatcliffActive LearningMaterials Science

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

    Apr 22, 2026Davi Febba, William A. Callahan, Anna Sacchi +1Active LearningAutonomous Experimentation

  5. MIND: AI Co-Scientist for Material Research

    Apr 15, 2026Geonhee Ahn, Donghyun Lee, Hayoung Doo +3AI Agents for Scientific DiscoveryAutonomous Experimentation

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

    Apr 13, 2026Yuxing Fei, Bernardus Rendy, Xiaochen Yang +7Autonomous ExperimentationLaboratory Automation

  7. Autonomous Diffractometry Enabled by Visual Reinforcement Learning

    Apr 13, 2026J. Oppliger, M. Stifter, A. Rüegg +7Autonomous ExperimentationLaboratory Automation

  8. Camyla: Scaling Autonomous Research in Medical Image Segmentation

    Apr 12, 2026Yifan Gao, Haoyue Li, Feng Yuan +3Autonomous Research AgentsAutonomous Experimentation

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

    Apr 7, 2026Yu Li, Chenyang Shao, Xinyang Liu +13Autonomous ExperimentationAutonomous Research Agents

  10. PATHFINDER: Multi-objective discovery in structural and spectral spaces

    Apr 5, 2026Kamyar Barakati, Boris N. Slautin, Utkarsh Pratiush +2Autonomous ExperimentationMulti-Objective Optimization

  11. Efficient and Principled Scientific Discovery through Bayesian Optimization: A Tutorial

    Apr 1, 2026Zhongwei Yu, Rasul Tutunov, Alexandre Max Maraval +13Bayesian OptimizationScientific Discovery

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

    Mar 31, 2026Jawad Chowdhury, Ganesh Narasimha, Jan-Chi Yang +4Active LearningPhysics-Informed ML

  13. Toward Full Autonomous Laboratory Instrumentation Control with Large Language Models

    Mar 25, 2026Yong Xie, Kexin He, Andres Castellanos-GomezLaboratory AutomationAutonomous Experimentation

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

    Mar 25, 2026Xiangyi Wei, Fei Wang, Haotian Zhang +6Laboratory AutomationAutonomous Experimentation

  15. Toward an automated science of the mind

    Mar 22, 2026Akshay K. Jagadish, Milena Rmus, Kristin Witte +3Autonomous Scientific DiscoveryScientific Discovery

  16. Embodied Science: Closing the Discovery Loop with Agentic Embodied AI

    Mar 20, 2026Xiang Zhuang, Chenyi Zhou, Kehua Feng +10AI Agents for Scientific DiscoveryAutonomous Experimentation

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

    Mar 17, 2026Utkarsh Pratiush, Kamyar Barakati, Boris N. Slautin +4Deep Kernel LearningScanning Transmission Electron Microscopy

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

    Mar 17, 2026Sergio Barrachina-Muñoz, Marc Carrascosa-Zamacois, Horacio Bleda +6Autonomous ExperimentationWireless Communications

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

    Mar 13, 2026Arpan Biswas, Hiroshi Funakubo, Yongtao LiuAutonomous ExperimentationBayesian Optimization

  20. Large Language Model-Assisted Superconducting Qubit Experiments

    Mar 9, 2026Shiheng Li, Jacob M. Miller, Phoebe J. Lee +14Autonomous ExperimentationLanguage Model-Based Control

  21. BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

    Mar 1, 2026Yuyang Liu, Jingya Wang, Liuzhenghao Lv +1Autonomous ExperimentationNeuro-Symbolic Planning

  22. A Robotic Testing Platform for Pipelined Discovery of Resilient Soft Actuators

    Feb 24, 2026Ang Li, Alexander Yin, Alexander White +6Soft RoboticsAutonomous Experimentation

  23. Toward a Fully Autonomous, AI-Native Particle Accelerator

    Feb 19, 2026Chris TennantAI ControlAutonomous Experimentation

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

    Sep 21, 2025Thorsten Hellert, Drew Bertwistle, Simon C. Leemann +2AI for ScienceAgentic Workflows