An agentic artificially intelligent X-ray scientist

Machine Learning


  • Chen, Z. et al. Machine learning on neutron and x-ray scattering and spectroscopies. Chem. Phys. Rev. 2, 031301 (2021).

    Article 

    Google Scholar 

  • Kochkov, D. Machine learning–accelerated computational fluid dynamics. Proc. Natl Acad. Sci. USA 118, e2101784118 (2021).

    Article 
    MathSciNet 

    Google Scholar 

  • Jumper, J. Highly accurate protein structure prediction with alphafold. Nature 596, 583–589 (2021).

    Article 

    Google Scholar 

  • Chitturi, S. Capturing dynamical correlations using implicit neural representations. Nat. Commun. 14, 5852 (2023).

    Article 

    Google Scholar 

  • Wang, H. Scientific discovery in the age of artificial intelligence. Nature 620, 47–60 (2023).

    Article 

    Google Scholar 

  • Li, J. & Lopez, S. A. Machine learning accelerated photodynamics simulations. Chem. Phys. Rev. 4, 031309 (2023).

    Article 

    Google Scholar 

  • Plumley, R. On ultrafast X-ray scattering methods for magnetism. Adv. Phys. X 9, 2423935 (2024).

    Google Scholar 

  • Li, H. Machine learning-accelerated discovery of heat-resistant polysulfates for electrostatic energy storage. Nat. Energy 10, 90–100 (2025).

    Article 

    Google Scholar 

  • Yamawaki, M., Ohnishi, M., Ju, S. & Shiomi, J. Multifunctional structural design of graphene thermoelectrics by Bayesian optimization. Sci. Adv. 4, eaar4192 (2018).

    Article 

    Google Scholar 

  • Lookman, T., Balachandran, P. V., Xue, D. & Yuan, R. Active learning in materials science with emphasis on adaptive sampling using uncertainties for targeted design. npj Comput. Mater. 5, 21 (2019).

    Article 

    Google Scholar 

  • McMichael, R. D., Dushenko, S. & Blakley, S. M. Sequential Bayesian experiment design for adaptive Ramsey sequence measurements. J. Appl. Phys. 130, 144401 (2021).

    Article 

    Google Scholar 

  • Ament, S. Autonomous materials synthesis via hierarchical active learning of nonequilibrium phase diagrams. Sci. Adv. 7, eabg4930 (2021).

    Article 

    Google Scholar 

  • MacLeod, B. P. A self-driving laboratory advances the pareto front for material properties. Nat. Commun. 13, 995 (2022).

    Article 

    Google Scholar 

  • Szymanski, N. J. An autonomous laboratory for the accelerated synthesis of novel materials. Nature 624, 86–91 (2023).

    Article 

    Google Scholar 

  • Teixeira Parente, M. Active learning-assisted neutron spectroscopy with log-gaussian processes. Nat. Commun. 14, 2246 (2023).

    Article 

    Google Scholar 

  • Chen, Z. Bayesian experimental design and parameter estimation for ultrafast spin dynamics. Mach. Learn. Sci. Technol. 4, 045056 (2023).

    Article 

    Google Scholar 

  • Chen, Z. et al. Implicit neural representations for experimental steering of advanced experiments. Cell Rep. Phys. Sci. 6, 102333 (2025).

    Article 

    Google Scholar 

  • Chu, T., Estrada, J. B. & Bryngelson, S. H. Bayesian optimal design accelerates discovery of soft material properties from bubble dynamics. Comput. Mech. 76, 431–447 (2025).

    Article 
    MathSciNet 

    Google Scholar 

  • Nair, A. S. & Foppa, L. A critical examination of active learning workflows in materials science. Digit. Discov. https://doi.org/10.1039/D6DD00081A (2026).

    Article 

    Google Scholar 

  • Karpovich, C., Pan, E. & Olivetti, E. A. Deep reinforcement learning for inverse inorganic materials design. npj Comput. Mater. 10, 287 (2024).

    Article 

    Google Scholar 

  • Yotsumoto, Y., Nakajima, Y., Takamoto, R., Takeichi, Y. & Ono, K. Autonomous robotic experimentation system for powder X-ray diffraction. Digit. Discov. 3, 2523–2532 (2024).

    Article 

    Google Scholar 

  • Bloor, M. Control-informed reinforcement learning for chemical processes. Ind. Eng Chem. Res. 64, 4966–4978 (2025).

    Article 

    Google Scholar 

  • Nguyen, T. M. & Truong, T. N. Inverse design using goal-conditioned reinforcement learning for organic semiconductor materials from benzene and thiophene-based polycyclic aromatic compounds. npj Comput. Mater. 11, 372 (2025).

    Article 

    Google Scholar 

  • Masina, S. Automated high-throughput high-resolution X-ray diffraction capabilities at SSRL BL 2-1. Struct. Dyn. 12, A243 (2025).

    Article 

    Google Scholar 

  • Crain, C. A. et al. Design of a robot-automated flat plate/reflection geometry X-ray diffraction setup for accelerated materials discovery and structural screening. Rev. Sci. Instrum. 96, 023904 (2025).

    Article 

    Google Scholar 

  • Zhang, Y. et al. A comprehensive survey of scientific large language models and their applications in scientific discovery. In Proc. 2024 Conference on Empirical Methods in Natural Language Processing (eds Al-Onaizan, Y. et al.) 8783–8817 (Association for Computational Linguistics, Miami, 2024); https://doi.org/10.18653/v1/2024.emnlp-main.498

  • Ghafarollahi, A. & Buehler, M. J. ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning. Digit. Discov. 3, 1389–1409 (2024).

    Article 

    Google Scholar 

  • Lei, G., Docherty, R. & Cooper, S. J. Materials science in the era of large language models: a perspective. Digit. Discov. 3, 1257–1272 (2024).

    Article 

    Google Scholar 

  • Schmidgall, S. et al. Agent laboratory: using LLM agents as research assistants. in Findings of the Association for Computational Linguistics: EMNLP 2025 (eds Christodoulopoulos, C., Chakraborty, T., Rose, C. & Peng, V.) 5977–6043 (Association for Computational Linguistics, Suzhou, China, 2025); https://doi.org/10.18653/v1/2025.findings-emnlp.320

  • Boiko, D. A., MacKnight, R., Kline, B. & Gomes, G. Autonomous chemical research with large language models. Nature 624, 570–578 (2023).

    Article 

    Google Scholar 

  • Dai, T. Autonomous mobile robots for exploratory synthetic chemistry. Nature 635, 890–897 (2024).

    Article 

    Google Scholar 

  • Fushimi, K. Development of the autonomous lab system to support biotechnology research. Sci. Rep. 15, 6648 (2025).

    Article 

    Google Scholar 

  • Yang, J. Zero-shot autonomous microscopy for scalable and intelligent characterization of 2D materials. ACS Nano 19, 35493–35502 (2025).

    Article 

    Google Scholar 

  • Zhang, Z. et al. A multimodal robotic platform for multi-element electrocatalyst discovery. Nature 647, 390–396 (2025).

    Article 

    Google Scholar 

  • Qu, Y. et al. CRISPR-GPT for agentic automation of gene-editing experiments. Nat. Biomed. Eng 10, 245–258 (2026).

    Article 

    Google Scholar 

  • Song, T. A multiagent-driven robotic ai chemist enabling autonomous chemical research on demand. J. Am. Chem. Soc. 147, 12534–12545 (2025).

    Article 

    Google Scholar 

  • Tom, G. Self-driving laboratories for chemistry and materials science. Chem. Rev. 124, 9633–9732 (2024).

    Article 

    Google Scholar 

  • Ramos, M. C., Collison, C. J. & White, A. D. A review of large language models and autonomous agents in chemistry. Chem. Sci. 16, 2514–2572 (2025).

    Article 

    Google Scholar 

  • Kim, M. J. et al. OpenVLA: an open-source vision-language-action model. In Proc. 8th Conference on Robot Learning (eds Agrawal, P. et al.) 2679–2713 (PMLR, 2025); https://proceedings.mlr.press/v270/kim25c.html

  • Ruan, Y. An automatic end-to-end chemical synthesis development platform powered by large language models. Nat. Commun. 15, 10160 (2024).

    Article 

    Google Scholar 

  • Mon-Williams, R., Li, G., Long, R., Du, W. & Lucas, C. G. Embodied large language models enable robots to complete complex tasks in unpredictable environments. Nat. Mach. Intell. 7, 592–601 (2025).

    Article 

    Google Scholar 

  • Wei, J. et al. Chain-of-thought prompting elicits reasoning in large language models. Adv. Neural Inf. Process. Syst. 35, 24824–24837 (2022).

    Article 

    Google Scholar 

  • Yao, S. et al. Tree of thoughts: deliberate problem solving with large language models. Adv. Neural Inf. Process. Syst. 36, 11809–11822 (2023).

    Article 

    Google Scholar 

  • Singh, I. et al. ProgPrompt: generating situated robot task plans using large language models. In 2023 IEEE International Conference on Robotics and Automation (IEEE, 2023); https://doi.org/10.1109/ICRA48891.2023.10161317

  • Yao, S. et al. ReAct: synergizing reasoning and acting in language models. In The 11th International Conference on Learning Representations (2023); https://openreview.net/forum?id=WE_vluYUL-X

  • Minaee, S. et al. Large language models: a survey. Preprint at https://arxiv.org/abs/2402.06196 (2024).

  • Hou, X., Zhao, Y., Wang, S. & Wang, H. Model context protocol (MCP): landscape, security threats, and future research directions. ACM Trans. Softw. Eng Methodol. https://doi.org/10.1145/3796519 (2025).

    Article 

    Google Scholar 

  • Ma, Y. et al. SciAgent: tool-augmented language models for scientific reasoning. In Proc. 2024 Conference on Empirical Methods in Natural Language Processing (eds Al-Onaizan, Y. et al.) 15701–15736 (Association for Computational Linguistics, 2024); https://doi.org/10.18653/v1/2024.emnlp-main.880

  • Wu, J., Zhu, J., Liu, Y., Xu, M. & Jin, Y. Agentic reasoning: a streamlined framework for enhancing LLM reasoning with agentic tools. In Proc. 63rd Annual Meeting of the Association for Computational Linguistics Vol. 1 (eds Che, W. et al.) 28489–28503 (2025); https://doi.org/10.18653/v1/2025.acl-long.1383

  • Corrao, A. A. et al. A modular framework for collaborative human-AI, multi-modal and multi-beamline synchrotron experiments. Preprint at https://arxiv.org/abs/2509.22959 (2025).

  • Ding, L. & Do, C. SasAgent: multi-agent AI system for small-angle scattering data analysis. J. Appl. Cryst. 59, 578–585 (2026).

    Article 

    Google Scholar 

  • Yao, L. et al. Operationalizing serendipity: multi-agent AI workflows for enhanced materials characterization with theory-in-the-loop. Preprint at https://arxiv.org/abs/2508.06569 (2025).

  • Hellert, T., Bertwistle, D., Leemann, S. C., Sulc, A. & Venturini, M. Agentic artificial intelligence for multistage physics experiments at a large-scale user facility particle accelerator. Phys. Rev. Res. 8, L012017 (2026).

    Article 

    Google Scholar 

  • Vriza, A., Prince, M. H., Zhou, T., Chan, H. & Cherukara, M. J. Operating advanced scientific instruments with AI agents that learn on the job. npj Comput. Mater. 12, 160 (2026).

    Article 

    Google Scholar 

  • Kotani, A. & Shin, S. Resonant inelastic X-ray scattering spectra for electrons in solids. Rev. Mod. Phys. 73, 203 (2001).

    Article 

    Google Scholar 

  • Ihee, H., Wulff, M., Kim, J. & Adachi, S. I. Ultrafast X-ray scattering: structural dynamics from diatomic to protein molecules. Int. Rev. Phys. Chem. 29, 453–520 (2010).

    Article 

    Google Scholar 

  • Bostedt, C. et al. Linac coherent light source: the first five years. Rev. Mod. Phys. 88, 015007 (2016).

    Article 

    Google Scholar 

  • Meisburger, S. P., Thomas, W. C., Watkins, M. B. & Ando, N. X-ray scattering studies of protein structural dynamics. Chem. Rev. 117, 7615–7672 (2017).

    Article 

    Google Scholar 

  • Mühlbauer, S. et al. Magnetic small-angle neutron scattering. Rev. Mod. Phys. 91, 015004 (2019).

    Article 
    MathSciNet 

    Google Scholar 

  • Zhang, J. N. Trace doping of multiple elements enables stable battery cycling of LiCoO2 at 4.6 V. Nat. Energy 4, 594–603 (2019).

    Article 

    Google Scholar 

  • Cao, C. Emerging X-ray imaging technologies for energy materials. Mater. Today 34, 132–147 (2020).

    Article 

    Google Scholar 

  • Allen, A. J. Selected advances in small-angle scattering and applications they serve in manufacturing, energy and climate change. J. Appl. Cryst. 56, 787–800 (2023).

    Article 

    Google Scholar 

  • Hamdalla, T. A. Synchrotron-based operando X-ray diffraction and X-ray absorption spectroscopy study of LiCo0.5Fe0.5PO4 mixed d-metal olivine cathode. Sci. Rep. 13, 2169 (2023).

    Article 

    Google Scholar 

  • Lee, Y., Oang, K. Y., Kim, D. & Ihee, H. A comparative review of time-resolved X-ray and electron scattering to probe structural dynamics. Struct. Dyn. 11, 031301 (2024).

    Article 

    Google Scholar 

  • Sun, T. et al. Pinpointing chemomechanical origins of Na cathode degradation. J. Am. Chem. Soc. 147, 21375–21384 (2025).

    Article 

    Google Scholar 

  • Galayda, J. N. et al. The LCLS-II: a high power upgrade to the LCLS. In 9th International Particle Accelerator Conference (eds Koscielniak, S. et al.) 18–23 (JACoW, 2018); https://doi.org/10.18429/JACoW-IPAC2018-MOYGB2

  • Zhang, H. The linac coherent light source ii photoinjector laser infrastructure. High Power Laser Sci. Eng 12, e51 (2024).

    Article 

    Google Scholar 

  • Kerby, J. The advanced photon source upgrade: a brighter future for X-ray science. Synchrotron Radiat. News 36, 26–27 (2023).

    Article 

    Google Scholar 

  • Harrington, G. F. & Santiso, J. Back-to-basics tutorial: X-ray diffraction of thin films. J. Electroceram. 47, 141–163 (2021).

    Article 

    Google Scholar 

  • You, H. Angle calculations for a ‘4S + 2D’ six-circle diffractometer. Appl. Crystallogr. 32, 614–623 (1999).

    Article 

    Google Scholar 

  • Certified scientific software SPEC—X-ray diffraction software. Certified Scientific Software https://www.certif.com/content/spec/ (2017).

  • Brown, T. et al. Language models are few-shot learners. Adv. Neural Inf. Process. Syst. 33, 1877–1901 (2020).

    Google Scholar 

  • Dong, Q. et al. A survey on in-context learning. In Proc. 2024 Conference on Empirical Methods in Natural Language Processing (eds Al-Onaizan, Y. et al.) 1107–1128 (Association for Computational Linguistics, 2024); https://doi.org/10.18653/v1/2024.emnlp-main.64

  • Weihrich, R., Anusca, I. & Zabel, M. Half-antiperovskites: structure and type-antitype relations of shandites M3/2AS (M: Co, Ni; A: In, Sn). Zeitschrift Fur Anorganische Und Allgemeine Chemie 631, 1463–1470 (2005).

    Article 

    Google Scholar 

  • Kanagaraj, M., Ning, J. & He, L. Topological Co3Sn2S2 magnetic weyl semimetal: from fundamental understanding to diverse fields of study. Rev. Phys. 8, 100072 (2022).

    Article 

    Google Scholar 

  • Horton, M. K. et al. Accelerated data-driven materials science with the Materials Project. Nat. Mater. 24, 1522–1532 (2025).

    Article 

    Google Scholar 

  • Jain, A. et al. Commentary: The Materials Project: a materials genome approach to accelerating materials innovation. APL Mater. 1, 011002 (2013).

    Article 

    Google Scholar 

  • Introducing Claude 4. Anthropic https://www.anthropic.com/news/claude-4 (2025).

  • Comanici, G. et al. Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. Preprint at https://arxiv.org/abs/2507.06261 (2025).

  • Vaqueiro, P. & Sobany, G. G. A powder neutron diffraction study of the metallic ferromagnet Co3Sn2S2. Solid State Sci. 11, 513–518 (2009).

    Article 

    Google Scholar 

  • Gražulis, S. Crystallography open database (COD): an open-access collection of crystal structures and platform for world-wide collaboration. Nucleic Acids Res. 40, D420–D427 (2012).

    Article 

    Google Scholar 

  • Lewis, P. et al. Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv. Neural Inf. Process. Syst. 33, 9459–9474 (2020).

    Google Scholar 

  • Luo, H. et al. Beyond context limits: subconscious threads for long-horizon reasoning. Preprint at https://arxiv.org/abs/2507.16784 (2025).

  • Granade, C. E., Ferrie, C., Wiebe, N. & Cory, D. G. Robust online Hamiltonian learning. New J. Phys. 14, 103013 (2012).

    Article 
    MathSciNet 

    Google Scholar 

  • Huan, X. & Marzouk, Y. M. Simulation-based optimal Bayesian experimental design for nonlinear systems. J. Comput. Phys. 232, 288–317 (2013).

    Article 
    MathSciNet 

    Google Scholar 

  • McMichael, R. D. & Blakley, S. M. Simplified algorithms for adaptive experiment design in parameter estimation. Phys. Rev. Appl. 18, 054001 (2022).

    Article 

    Google Scholar 

  • Ong, S. P. Python materials genomics (pymatgen): a robust, open-source Python library for materials analysis. Comput. Mater. Sci. 68, 314–319 (2013).

    Article 

    Google Scholar 

  • De Graef, M. & McHenry, M. E. Structure of Materials: An Introduction to Crystallography, Diffraction and Symmetry (Cambridge Univ. Press, 2012); https://doi.org/10.1017/CBO9781139051637

  • Introducing the Model Context Protocol. Anthropic https://www.anthropic.com/news/model-context-protocol (2024).

  • Avila, D. et al. LibreChat. GitHub https://github.com/danny-avila/LibreChat (2025).

  • Chen, Z. et al. Data for an agentic artificially intelligent X-ray scientist. Zenodo https://doi.org/10.5281/zenodo.20017861 (2026).

  • Chen, Z. et al. Code for an agentic artificially intelligent X-ray scientist. Zenodo https://doi.org/10.5281/zenodo.20017991 (2026).



  • Source link