A Multiagent-Driven Robotic AI Chemist Enabling Autonomous Chemical Research On Demand
Open accessThe DOI matches its Crossref record; 82 of the 82 references it cites were found in a registry or an index.
Abstract
The successful integration of large language models (LLMs) into laboratory workflows has demonstrated robust capabilities in natural language processing, autonomous task execution, and collaborative problem-solving. This offers an exciting opportunity to realize the dream of autonomous chemical research on demand. Here, we report a robotic AI chemist powered by a hierarchical multiagent system, ChemAgents, based on an on-board Llama-3.1-70B LLM, capable of executing complex, multistep experiments with minimal human intervention. It operates through a Task Manager agent that interacts with human researchers and coordinates four role-specific agents─Literature Reader, Experiment Designer, Computation Performer, and Robot Operator─each leveraging one of four foundational resources: a comprehensive Literature Database, an extensive Protocol Library, a versatile Model Library, and a state-of-the-art Automated Lab. We demonstrate its versatility and efficacy through six experimental tasks of varying complexity, ranging from straightforward synthesis and characterization to more complex exploration and screening of experimental parameters, culminating in the discovery and optimization of functional materials. Additionally, we introduce a seventh task, where ChemAgents is deployed in a new robotic chemistry lab environment to autonomously perform photocatalytic organic reactions, highlighting ChemAgents's scalability and adaptability. Our multiagent-driven robotic AI chemist showcases the potential of on-demand autonomous chemical research to accelerate discovery and democratize access to advanced experimental capabilities across academic disciplines and industries.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The text we found for this paper looks like another document, so the self-check wasn’t run.
Citations
Cites
LLaMA: Open and Efficient Foundation Language Models
Touvron, H., Lavril, T., Izacard, G., Martinet, X., Lachaux, M.-A., Lacroix, T., Rozière, B., Goyal, N., Hambro, E., Azhar, F., et al. (2023) · arXiv · doi:10.48550/arxiv.2302.13971 · Cited by 4,602
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology · doi:10.1145/3586183.3606763 · Cited by 2,187
Generative Agents: Interactive Simulacra of Human Behavior
Park, J. S., O'Brien, J. C., Cai, C. J., Morris, M. R., Liang, P., & Bernstein, M. S. (2023) · arXiv · doi:10.48550/arxiv.2304.03442 · Cited by 2,173
A Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Dong, Z., Hou, Y., Zhang, B., Min, Y., Zhang, J., Liu, P., et al. (2026) · Frontiers of Computer Science · doi:10.1007/s11704-026-60308-3 · Cited by 2,093
Self-citationA Survey of Large Language Models
Zhao, W. X., Zhou, K., Li, J., Tang, T., Wang, X., Hou, Y., Min, Y., Zhang, B., Zhang, J., Dong, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.18223 · Cited by 2,090
Self-citationA survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941
A Survey on Large Language Model based Autonomous Agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2308.11432 · Cited by 1,925
Large Language Model based Multi-Agents: A Survey of Progress and Challenges
Guo, T., Chen, X., Wang, Y., Chang, R., Pei, S., Chawla, N. V., Wiest, O., & Zhang, X. (2024) · arXiv · doi:10.48550/arxiv.2402.01680 · Cited by 1,713 · cited 1×
“By enabling collaboration and coordination among agents, each with a unique role and associated abilities (Figure 1), ChemAgents amplifies the effectiveness of single LLM agents, allowing them to collectively tackle complex tasks and achieve defined objectives 57-61 .”
Self-citationBurger, B., Maffettone, P. M., Gusev, V. V., Aitchison, C. M., Bai, Y., Wang, X., Li, X., Alston, B. M., Li, B., Clowes, R., et al. (2020) · Nature · doi:10.1038/s41586-020-2442-2 · Cited by 1,516 · cited 2×
“As autonomous chemistry evolves from isolated autonomous labs 43,44 to coordinated, cloud-based systems 64 , and, in the future, to advanced networks of Intelligent Scientist Systems 65 , our multi-agent-driven robotic AI chemist aligns closely with this trajectory and will help accelerate these…”
Reduction of aryl halides by consecutive visible light-induced electron transfer processes
Ghosh, I., Ghosh, T., Bardagi, J. I., & König, B. (2014) · Science · doi:10.1126/science.1258232 · Cited by 1,250
Research works printed but not linked: 4
- Chowdhery A., 2023, J. Mach. Learn. Res., 24, 1
- Shinn N., 2023, Adv. Neural Inf. Process. Syst., 36, 8634
- Shen Y., 2023, Adv. Neural Inf. Process. Syst., 36, 38154
- Driess D., 2023, Proc. 40th Int. Conf. Mach. Learn., 202, 8469
Cited by
Items 101–200 of 210
Are we there yet? Adventures on a road trip through machine learning as a computational chemist
Kulik, H. J. (2025) · APL Computational Physics · doi:10.1063/5.0297853 · Cited by 3
Development of AI-eChemist Laboratory
Tan, Y., Chen, L., Shan, X., Tu, Y., Wang, P., Xu, J., Gao, H., & Zhou, M. (2026) · AI Agent · doi:10.20517/aiagent.2026.15 · Cited by 3
Self-citationXu, L., Wang, J., Zhang, C., Huang, J. Y., Zhou, J., Ren, Z., Yao, J., Li, J., Jiang, H., Huang, M., et al. (2026) · ACS Catalysis · doi:10.1021/acscatal.6c03989 · Cited by 3
Machine Learning and Autonomous Systems for Accelerated Synthesis
McDonald, M. A., & Jensen, K. F. (2026) · Annual Review of Analytical Chemistry · doi:10.1146/annurev-anchem-071924-103847 · Cited by 3
Artificial Intelligence as the Next Visionary in Liquid Crystal Research
Astam, M. O., L'Karkouri, O., & Liu, D. (2026) · Advanced Functional Materials · doi:10.1002/adfm.202529976 · Cited by 3
Self-citationCai, R., Gao, T., Fang, F., & Liu, Y. (2026) · Chemistry of Materials · doi:10.1021/acs.chemmater.5c03513 · Cited by 3
Kusne, A. G., & McDannald, A. (2026) · Communications Materials · doi:10.1038/s43246-026-01219-5 · Cited by 3
“…manuals to assist users with instrument control 49 , to perform literature review 50 , to reproduce experiments from literature 24 , to run and analyze physics-based simulations 21 , and most recently, to control mobile robots interacting with chemistry synthesis and characterization tools 51 .”
Self-driving laboratories need an autonomy safety harness
Chen, L., Li, X., Lin, Q., & Jiang, J. (2026) · Nature Synthesis · doi:10.1038/s44160-026-01120-6 · Cited by 3
Self-citationGenerative AI for environmental mass spectrometry: Opportunities and challenges
Li, W., & Hu, B. (2026) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2026.119023 · Cited by 2
Vasina, M., Kovar, D. R., Kizovský, M., Lacko, D., Vaňáček, P., Herich, M., Volf, E., Drdla, L., Cabalová, S., Sikorová, P., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.06.04.730034 · Cited by 2
MOFReasoner: think like a scientist—a reasoning large language model via knowledge distillation
Bai, X., Zheng, Z., Zhang, X., Wang, H.-T., Yang, R., & Li, J. (2026) · Digital Discovery · doi:10.1039/d5dd00429b · Cited by 2
Self-citationOperating advanced scientific instruments with AI agents that learn on the jobPreprint
Vriza, A., Prince, M. H., Zhou, T., et al. (2025) · Research Square · doi:10.21203/rs.3.rs-7706574/v1 · Cited by 2
Optimizing Model Learning Performance on a Challenging Heck Reaction Yield Data Set
Wang, S., Liu, Y., Zhao, W., & Li, Y. (2025) · The Journal of Organic Chemistry · doi:10.1021/acs.joc.5c01641 · Cited by 2
Programming nanozyme identity for precision catalytic medicine by tailoring the bio-nano interface
Liu, J., Wang, Y., Xie, Y., Zhang, C., Zhang, J., Chen, L., Zhao, L., Li, B., Yang, H., & Yong, Y. (2026) · International Journal of Pharmaceutics · doi:10.1016/j.ijpharm.2026.127101 · Cited by 2
Self-citationZhang, J. (2026) · ACS Energy Letters · doi:10.1021/acsenergylett.6c01391 · Cited by 3
Recent Advances in Artificial Intelligence in Organic Electronic Research
Zhang, Q., Su, Z., Zhang, H., Sun, Y. W., & Hu, W. (2026) · Advanced Materials · doi:10.1002/adma.73151 · Cited by 2
“Similarly, Song et al. developed ChemAgents [68], a multi-agent system based on Llama-3.”
Inside the ‘self-driving’ lab revolution
Brazil, R. (2026) · Nature · doi:10.1038/d41586-026-00974-2 · Cited by 2
Translating Nature’s Design Rules: How Catalysis and Life Science Guide Molecular Catassembly
Qu, H., Wang, F., Lei, Z., Wang, X., Yang, L., Cao, X., Fan, C., & Tian, Z. (2025) · JACS Au · doi:10.1021/jacsau.5c01001 · Cited by 2
Opportunities of Large Language Models in the Development of Organic Electrosynthesis
Yu, Z., Yang, Q., & Mo, Y. (2025) · ACS electrochemistry. · doi:10.1021/acselectrochem.5c00377 · Cited by 2
AI-Informed Solvation Engineering for Thermogalvanic Electrolytes with High Thermopower
Wu, S., Luo, Y., Niu, S., Lin, W., & Fang, C. (2025) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.5c02903 · Cited by 2
Self-citationTeLLAgent: a dual-agent framework for reliable scientific discovery with tool-enhanced LLMs
Sun, J., Zhou, J., Wang, H., Liu, W., Yuan, J., Wang, Y., Xie, T., Tan, L., Zhang, H., Zou, Y., et al. (2026) · Chemical Science · doi:10.1039/d5sc09883a · Cited by 3
Differentiable hybrid force fields support scalable autonomous electrolyte discovery
Wang, X., Chen, J., Zhu, Z., & Zhong, P. (2026) · Journal of Energy Chemistry · doi:10.1016/j.jechem.2026.05.049 · Cited by 2
“However, coordinating these heterogeneous information streams demands context-dependent judgment that cannot be captured by a fixed protocol.”
From Chatbots to Chemists: Autonomous Agents for Heterogeneous Catalysis
Jin, M., Liao, C., Xu, Z., Song, Y., He, R., Zhang, Y., Hu, X., & Shen, Z. (2026) · ACS Catalysis · doi:10.1021/acscatal.6c02268 · Cited by 4
From execution loop to reasoning loop in autonomous materials research
Tan, Z., Qian, L., Wang, Y., & Ran, N. (2026) · AI Agent · doi:10.20517/aiagent.2026.13 · Cited by 2
Scientific Engineering of Self-Driving Laboratories at Scale
Li, X., Chen, L., Liu, D., Zhu, Z., Zhang, X., Guo, L., Ge, L., Zhang, H., Liu, Y., Li, J., et al. (2026) · ACS Nano · doi:10.1021/acsnano.6c15286 · Cited by 2
Self-citationAI agents for MOFs and COFs discovery
Yu, J., Jiang, Z., & He, D. (2026) · AI Agent · doi:10.20517/aiagent.2026.33 · Cited by 2
PRISM: protocol refinement through intelligent simulation modeling
Hsu, B., Setty, P. V., Butler, R. M., Lewis, R., Stone, C. R., Weinberg, R., Brettin, T. S., Stevens, R. L., Foster, I. T., & Ramanathan, A. (2026) · Digital Discovery · doi:10.1039/d6dd00004e · Cited by 3
Agentic AI for Accelerated Materials Characterization in Synchrotron Science
Li, T., & Li, J. (2025) · Photon Science · doi:10.1021/photonsci.5c00012 · Cited by 2
Kalinin, S. V., Slautin, B. N., Liu, Y., Foadian, E., Duscher, G. J., Ahmadi, M., & Bazhirov, T. (2026) · ChemRxiv · doi:10.26434/chemrxiv.10002018/v1 · Cited by 2
Wang, Q., Wang, Y., & Gong, X. (2026) · Pharmaceuticals · doi:10.3390/ph19020264 · Cited by 1
“For example, Clarissa Y. P. Wilding et al. [37] applied it to the optimization of RAFT polymerization to improve efficiency and sustainability, while Tao Song et al. [38] integrated this algorithm into multi-agent-driven robots to discover high-performance metal–organic high-entropy catalysts.”
Jarabo-Peñas, A., Bravo-Arrabal, J., Rolland, E. G. A., & Christensen, A. L. (2026) · International Conference on Unmanned Aircraft Systems (ICUAS) · doi:10.1109/icuas69441.2026.11598684 · Cited by 1
“Multi-agent LLM architectures with bounded, role-specific agents yield more predictable behavior than monolithic prompting [23], and peer-to-peer LLM dialogue has shown promise for collaborative task allocation [24], though scalability remains a challenge.”
Usability and extensibility: imperatives for next-generation LLM agents in chemistry
Bai, X., Zhang, X., Wang, H., Zheng, Z., & Li, J.-R. (2026) · Science China Chemistry · doi:10.1007/s11426-025-3262-6 · Cited by 1
Self-citationData-intelligent-driven exploration of robotic chemist systems
Jincheng, X., Chen, L., & Jiang, J. (2025) · Scientia Sinica Chimica · doi:10.1360/ssc-2025-0093 · Cited by 1
Self-citationThe converging moment of chemistry and artificial intelligence: a review and outlook
Zhang, W., Zhang, Y., Xiong, J., Zheng, M., & Chen, K. (2025) · Scientia Sinica Chimica · doi:10.1360/ssc-2025-0111 · Cited by 1
Application and progress of artificial intelligence agents in drug development
Zhao, D., & Hsieh, C. (2026) · Journal of Zhejiang University (Medical Sciences) · doi:10.3724/zdxbyxb-2025-0697 · Cited by 2
Applications of multi-agent systems in computational materials science
Ying, W., Zhong-Yi, L., & Zefeng, G. A. O. (2026) · Acta Physica Sinica · doi:10.7498/aps.75.20251687 · Cited by 1
Multi-Objective Optimization of Grasping Trajectories for Manipulator with Improved OMOPSO
Xu, Z. Y., Liu, T., Jin, D., Xu, W., Xu, M., Yi, H., Wu, Y., & Tan, P. (2026) · Symmetry · doi:10.3390/sym18020392 · Cited by 1
Zhang, Y., Lin, A., Zhou, C., Liu, J., Wang, Y., Zhu, X., Su, L., & Liao, K. (2026) · Organic Chemistry Frontiers · doi:10.1039/d6qo00026f · Cited by 1
Simulon: An AI ‐Assisted, PyTorch ‐Native Framework of Molecular Dynamics and Modeling
Jin, Z., Sun, X., Xi, X., & Nie, Z. (2026) · Journal of Computational Chemistry · doi:10.1002/jcc.70364 · Cited by 1
Xiang, J., Huang, Q., Zhang, X., Yang, T., Zhu, Z., Li, C., Cai, L., & Sun, Q. (2026) · Chemical Science · doi:10.1039/d6sc01168c · Cited by 3
Self-citationAfter the Interface: Relocating Human Agency in the Age of Conversational AI
Wu, M., & Yao, M. (2026) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3816046.3816301 · Cited by 2
Miyawaki, N., & Hitosugi, T. (2026) · Applied Physics Express · doi:10.35848/1882-0786/ae7176 · Cited by 1
Research progress of domain-specific large language models for chemical materials
Chen, W., Li, L., Xu, H., & Cheng, D. (2026) · Chinese Journal of Chemical Engineering · doi:10.1016/j.cjche.2026.05.013 · Cited by 1
Niu, Z., Zhao, W., Jackson, L., Cai, Q., Pinfield, V. J., Lin, W.-F., Wu, B., Luo, K., & Wang, Y. (2026) · 中国科学通报:英文版 · doi:10.1016/j.scib.2026.07.036 · Cited by 1
Autonomous laboratories for sustainable nanomaterials discovery
Jathar, A., Nawghare, B. R., & Ganure, K. A. (2026) · Next Materials · doi:10.1016/j.nxmate.2026.102883 · Cited by 2
Huang, J., Li, W., Cao, Y., Guo, M., Jin, H., & Liu, Y. (2026) · Food Research International · doi:10.1016/j.foodres.2026.120173 · Cited by 1
Zhang, S., Liang, D., Lei, Y., Luo, Y., & Shi, R. (2026) · Frontiers in Bioengineering and Biotechnology · doi:10.3389/fbioe.2026.1898243 · Cited by 2
“…bioprinting laboratories provide adjacent-field methodological inspiration from drug discovery, materials science, chemistry, and biofabrication, but they do not yet validate autonomous bioink preparation, printing, maturation, and functional testing (Song et al., 2025; Liu et al., 2026).”
Self-citationQuo Vadis? Scientific Discovery in the Age of Artificial Intelligence
Jedlička, P. (2026) · Teorie vědy / Theory of Science · doi:10.46938/tv.2026.728 · Cited by 1
Liu, B., Li, J., Xing, A., Luo, G., Lu, H. Y., Li, Q., Shi, Q., Rao, W., & Li, K. (2026) · TrAC Trends in Analytical Chemistry · doi:10.1016/j.trac.2026.119107 · Cited by 1
Atomic customization for water electrolysis
Wang, X., Yang, S., Liu, Y., Wang, Y., Chen, Y., Ren, A., Kang, Z., & Zhang, Y. (2026) · Chemical Society Reviews · doi:10.1039/d6cs00291a · Cited by 1
Dmitrienko, A. S., Douglas, E. T., Kobti, J.-L., Vukotic, K. R., Geauvreau, K., Patrick, B. O., & Vukotic, V. N. (2026) · Chem · doi:10.1016/j.chempr.2026.103283 · Cited by 1
Agentic AI systems for scientific discovery
Feng, B., Walther, P., Zhang, L., Coyle, R. A., Kim, S., Mandal, A., Zhang, Z., Papidocha, S. M., Kelmanson, A., Segura, D. M., et al. (2026) · Nature Reviews Methods Primers · doi:10.1038/s43586-026-00534-y · Cited by 3
“Hierarchical planning separates high-level goals from low-level executable steps; ChemAgents implements this through a Task Manager coordinating four role-specific subagents covering literature retrieval, experimental design, computation and robotic operation 95 .”
AI agents in drug discovery: A review of evolution, applications, and future directions
Das, S., Ferdaus, M. M., & Dam, T. (2026) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2026.109539 · Cited by 2
Cui, D.-X., Long, S.-Y., & Li, Q. (2025) · ChemRxiv · doi:10.26434/chemrxiv-2025-85wpr-v2 · Cited by 1
Automating Hypothesis Generation and Testing: Towards Self-driving Biology
Brunnsåker, D. (2025) · Chalmers Research (Chalmers University of Technology) · doi:10.63959/chalmers.dt/5755 · Cited by 1
ChemVLMate: a multimodal, dual-arm, seeing robotic chemist for adaptive synthesisPreprint
Song, T., Chen, W., Li, X., Lei, H., Zhang, L., Zhang, H., Zou, G., Chen, L., Shang, W., & Jiang, J. (2026) · ChemRxiv · doi:10.26434/chemrxiv.15001727/v1 · Cited by 1
Self-citationExperiment-as-Code Labs: A Declarative Stack for AI-Driven Scientific DiscoveryPreprint
Yang, Z., Chen, Y., Kon, P. T. J., Miao, T., Lin, H., Viswanathan, V., Koutra, D., & Chen, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.04375 · Cited by 1
“…Da Silva et al., 2024; Lara-Ceniceros et al., 2025) and industry companies in the US and around the world (Seifrid et al., 2022; Tom et al., 2024; Song et al., 2025; Zaki et al., 2025; Zhang et al., 2025a; Starkholm et al., 2023; Miret et al., 2025; Laws et al., 2024; Cooper et al., 2025; Burger…”
Large language models do not replace chemists in a closed-loop catalysis experimentPreprint
Cooper, A. I., Yeow, Q. J., Xiao, Z., Zhu, M., Cisse, A., Evangelopoulos, X., & Boott, C. E. (2026) · Research Square · doi:10.21203/rs.3.rs-10032842/v1 · Cited by 2
ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent ExperimentationPreprint
Qiu, J., Li, Y., & Wang, X. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.10792 · Cited by 1
Cui, D.-X., & Long, S.-Y. (2025) · ChemRxiv · doi:10.26434/chemrxiv-2025-85wpr
Spark LLM and the Scientific Research it empowers: Practice and Thoughts
Li, X. (2025) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3746027.3764191
From literature to lab protocols with knowledge-graph-guided large language models
Zhao, B., Li, Z., Zhang, Y., Song, T., Shi, Z., Lin, Q., Shang, W., Jiang, J., & Chen, L. (2026) · Digital Discovery · doi:10.1039/d6dd00001k
Self-citationWang, Y., Wang, H., Sun, Y., Liu, X., & Dong, F. (2025) · Environmental Science & Technology · doi:10.1021/acs.est.5c09256
Wang, S., Zhao, W., Zhou, M., Liu, T., Wang, Y., Shi, R., Wang, Y., & Zhang, Z. (2025) · Progress in Photovoltaics Research and Applications · doi:10.1002/pip.70060 · Cited by 1
Kutskaia, A. M., & Rodygin, K. S. (2026) · Physical Chemistry Chemical Physics · doi:10.1039/d5cp04214c
CMeval: Safety Assessment for Chemical Scenarios of Small Language ModelsPreprint
Zhou, Z., Wang, Q., Li, Y., Xing, W., & Zhou, Z. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6315405
Optical-visualization chemical vapor deposition systems for 2D materials
Huang, C., Hua, J., Jin, D., Xu, X., Wang, D., Wang, L., & Shao, X. (2026) · Trends in Chemistry · doi:10.1016/j.trechm.2026.01.005
An Automated Extraction System for Material Chemistry Experimental Protocols
Yang, F., Xu, F., Liang, H., Fan, X., Chen, L., Zhang, K., Li, X., Wu, L., & Wang, S. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7144-4_14
Self-citationLiu, F. T., Chen, Z., Hu, H., Li, C. C., Zhang, L., Liu, Z., & Chen, G. (2026) · ACS Nano · doi:10.1021/acsnano.5c20552
Application of multi-agent in energy materials research
Wang, J., Zhu, H., Li, P., Liu, C., Liu, Y., & Wan, J. (2026) · Chinese Science Bulletin (Chinese Version) · doi:10.1360/csb-2025-5793 · Cited by 2
Liu, C.-L., Yang, Y., & Wang, J. (2026) · Proceedings of the 2026 Asia-Pacific Intelligent Educational Technologies Conference · doi:10.1145/3796114.3796118
Yang, Z., Du, Y., Liu, D., & Cong, M. (2026) · Industrial Robot the international journal of robotics research and application · doi:10.1108/ir-12-2025-0466
Self-citationToward System- and Theory-Oriented Talent Cultivation in Computing
Zhang, Y., Ding, H., Tian, Y., Lian, D., Xu, H., & Li, X. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-7731-6_47
Yang, R., Zhou, D., Jia, Z., Han, Y., Tang, L., Jiang, Z., Tai, X., Cai, Y., Zhong, W., Lin, Y., et al. (2026) · Angewandte Chemie · doi:10.1002/ange.8794274
Self-citationLiu, J., Lin, A., Ma, C., Zhang, C., Yang, C., Zhang, Y., Zhou, C., Xue, K., Su, L., & Liao, K. (2026) · JACS Au · doi:10.1021/jacsau.6c00160
Large language models unlock knowledge flow networks across battery chemistries
Hu, X., & Zhou, Z. (2026) · Science China Chemistry · doi:10.1007/s11426-026-3431-x
Application and prospects of artificial intelligence in condensed matter structural chemistry
Gong, J., Zhao, Z., Yang, T., Yang, L., Ma, Z., & Wang, P. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-44921-5.00010-9
Lim, J., Lee, H., & Shin, D. (2026) · ACS Sensors · doi:10.1021/acssensors.6c00865
AI for electrocatalytic energy conversion: from atoms to industry
Yang, X., Wang, N., Guo, Z., Xu, C., Wang, X., Zhang, J. C., Huang, P., & Chen, Y. (2026) · Science China Materials · doi:10.1007/s40843-025-4074-6
“4c), where its internal “Literature Reader”, “Experiment Designer”, “Robot Operator”, and “Computation Performer” collaborate to achieve on-demand autonomous experimentation [53].”
Luo, Y. (2026) · Precision Chemistry · doi:10.1021/prechem.6c00070
Self-citationChoi, H., Kim, J. Y., Lim, H., & Jeon, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.20120
Multi-robot coordination for effective anomaly handling in self-driving laboratories
Yang, Y., Yang, J., Lu, H., Liu, H., & Gao, W. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115568
The Lab of the Future: An Industrial Infrastructure for Scalable Molecular Innovation
Yang, M., Li, L., Sun, G., Liu, Y., Shi, X., Liu, W., Zhang, P., Ma, J., & Wen, S. (2026) · National Materials · doi:10.1002/nam2.70009
Large language models as designers for autonomous research of anisotropic polymer thermocells
Liu, W., Wang, J., Yang, Z., Yuan, H., Wang, W., Gao, B., Tan, Q., Li, H., Ouyang, W., Liu, G., et al. (2026) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2026.103502 · Cited by 1
Reaction: Self-driving labs need models of the chemical world
Chen, L., Xie, Z., & Jiang, J. (2026) · Chem · doi:10.1016/j.chempr.2026.103196
Self-citationJin, S., Song, G., Xiang, H., Fu, Z., Zhang, X., Pei, J., Zhang, T., Fan, W., Wang, Q., & Zhang, D. (2026) · Journal of Energy Chemistry · doi:10.1016/j.jechem.2026.07.066
Self-citationLin, W., Zhang, H., Sun, J., Ling, C., Zhang, X., Li, Q., Zhou, Q., & Wang, J. (2026) · Journal of the American Chemical Society · doi:10.1021/jacs.6c11778
Self-citationi BonD: bond energy database embracing the era of artificial intelligence
Wang, S., Yang, Q., Luo, S., & Cheng, J. (2026) · Digital Discovery · doi:10.1039/d6dd00231e
Kohti laajennettavaa automaattista puolijohteiden karakterisointia ja analyysiä
Häkkänen, O. (2026) · Aaltodoc (Aalto University)
Yang, Y., Yang, J., Lu, H., Liu, H., & Gao, W. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3726436
“In scientific laboratory settings, building a multi-robot, multi-task scheduling system [4] and coordinating agents with specific roles [3], [26] can improve the e ffi ciency of complex chemical experiments in autonomous chemistry laboratories [16].”
InfluentialMolecular LLM Agents: From Architectural Design to Scientific AutonomyPreprint
Li, J., Zhang, W., Wang, W., Ren, Y., Liu, W., Mao, C., Li, Y., Bian, Y., Zheng, C., Wei, X., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.23104
LLM‐Powered AI Agents in Materials Science: From Autonomous Design to Autonomous Experimentation
Jiang, T., Zhang, Z., Nie, M., Zhu, D., Meng, E., Wu, H., & Mao, X. (2026) · Advanced Functional Materials · doi:10.1002/adfm.78275 · Cited by 1
Selyukov, А. S., Малова, Н. Н., & Hecht, M. E. (2026) · Scientific and Technical Information Processing · doi:10.3103/s0147688226700085
“…that control advanced robotic laboratories, in which AI acts as a fully autonomous researcher, capable of conducting specialized literature searches, performing calculations, planning multi-step reactions, and synthesizing new functional materials on demand with minimal human intervention [8].”
Zhao, Y., Song, T., Chen, L., Huang, Y., Sun, K., Han, W., Shen, M., Mao, C., Lan, P., Zhou, M. R., et al. (2026) · Journal of the American Chemical Society · doi:10.1021/jacs.6c13252
Self-citationMathekiso, E. R., Jewel, S., & Changjiang, Y. (2026) · Green Chemical Technology · doi:10.70322/gct.2026.10028
Sun, W., Xue, Y., Jiang, G., Zhang, B., Shi, W., Mohseni, M. M. M., & Mao, T. (2026) · Research Square · doi:10.21203/rs.3.rs-10968317/v1
Self-citationAPEXA: Execution-Integrity Enforcement for Multi-Agent LLM Automation of Synchrotron Data ReductionPreprint
Tripathi, P. K., Sharma, H., Chuang, A., & Cherukara, M. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.24165
“Single-instrument LLM-agent demonstrations include Coscientist [28], ChemCrow [29] (on ReAct [30]), VISION [7] for SAXS/WAXS, X-ray nanoprobes [8], and robotic chemistry [31], atop a broader self-driving-lab literature [32], [33], [34], [35], [36].”
Polymer Informatics in the Era of Foundation Models: From Representation to Autonomous DesignPreprint
He, J., & Li, Y. (2026) · ChemRxiv · doi:10.26434/chemrxiv.15009334/v2
Toward autonomous chemical discovery: agentic AI in organic synthesis and nanochemistry
Babu, B. H., Vutla, P. C., Mahimaluru, J., Chong, B. K. J., & Kambam, S. (2026) · Results in Engineering · doi:10.1016/j.rineng.2026.113180
Co‐Evolution of Humans, AI, and Robotics in Autonomous Materials Manufacturing
Zhao, Y., Li, W., & Chen, X. (2026) · National Materials · doi:10.1002/nam2.70017
Metadata
- Authors
- Song, T., Luo, M., Zhang, X., Chen, L., Huang, Y., Cao, J., Zhu, Q., Liu, D., Zhang, B., Zou, G., Zhang, G., Zhang, F., Shang, W., Fu, Y., Jiang, J., & Luo, Y.
- Affiliations
- University of Science and Technology of China (CN)
- Corresponding author
- Chen, Linjiang
- Zhang, Fei
- Shang, Weiwei
- Fu, Yao
- Jiang, Jun
- Luo, Yi
- ORCID
- Venue
- Journal of the American Chemical Society
- Publisher
- American Chemical Society (ACS)
- Published
- 2025-03-08
- Volume
- 147
- Issue
- 15
- Pages
- 12534-12545
- ISSN
- 0002-7863 (ISSN-L)
- 1520-5126
- OpenAlex
- W4408247476
- Cited by
- 171
- References
- 68
- Citations by year
- 2026: 112 · 2025: 59
- FWCI
- 36.12
- Type
- journal article
- Language
- en
- Open access
- Licence
- Locations
- Journal of the American Chemical Society (publishedVersion)
- PubMed (publishedVersion)
- University of Birmingham Research Portal (University of Birmingham) (publishedVersion, other-oa)
- Funders
- Natural Science Foundation of Henan Province (242300421138)
- National Key Research and Development Program of China (2024YFB3817302)
- National Natural Science Foundation of China (22025304, 22033007, 22103076, 22303091, U22A2056)
- Natural Science Foundation of Anhui Province (2108085QB63)
- Chinese Academy of Sciences (XDB0450302, YSBR-005)
- USTC Research Funds of the Double First-Class Initiative (YD9990002032)
- Joint Fund of Henan Province Science and Technology R&D Program (235200810107)
- Innovation Program for Quantum Science and Technology (2021ZD0303303)
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Social Sciences › Education › Various Chemistry Research Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- multi-agent systems, large language models, laboratory automation, task coordination, bibliographic databases, parameter screening
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A second model labelled each claim on 2026-11-11 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.