A review of large language models and autonomous agents in chemistry
Open accessThe DOI matches its Crossref record; 623 of the 623 references it cites were found in a registry or an index.
Abstract
This review examines the roles of large language models (LLMs) and autonomous agents in chemistry, exploring advancements in molecule design, property prediction, and synthesis automation.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures






Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The broader literature on autonomous scientific systems has already argued for more rigorous evaluation protocols and transparent tool interfaces [3,5,7-12].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [5]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In parallel, chemistry-oriented reviews have shown that large language models can move beyond text generation toward tool use, retrieval, planning, code execution, and multi-agent coordination [5-10].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [5]
The cited source says what the claim attributes to it.
In the citing paper
“To the best of our knowledge, no prior review has isolated simulation-driven, toolorchestrating AI agent workflows for materials discovery as a distinct evidence base with study-level extraction of autonomy, validation, and reproducibility [3-14].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [5]
The cited source says what the claim attributes to it.
In the citing paper
“The central challenge is not only to predict a property, but to manage the sequence of reasoning and action that connects a scientific objective to executable computational or experimental steps [2-10].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [5]
The cited source says what the claim attributes to it.
In the citing paper
“Other reviews concentrate on natural-language processing in materials science, large language models for materials and chemistry, reticular chemistry, or generative crystal-structure modeling [5,11-14].”
From From Scientific Copilots to Tool-Grounded Autonomy: AI Agents in Simulation-Driven Materials Discovery (2026) · cites this paper as [5]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Items 601–623 of 623
Robot chemist sparks row with claim it created new materials
Peplow, M. (2023) · Nature · doi:10.1038/d41586-023-03956-w · Cited by 3
Repeat After Me: Transformers are Better than State Space Models at Copying
Jelassi, S., Brandfonbrener, D., Kakade, S. M., & Malach, E. (2024) · arXiv · doi:10.48550/arxiv.2402.01032 · Cited by 3
MolTC: Towards Molecular Relational Modeling In Language ModelsPreprint
Fang, J., Zhang, S., Chang, W., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.03781 · Cited by 3
ACEGEN: Reinforcement learning of generative chemical agents for drug discoveryPreprint
Bou, A., Thomas, M., Dittert, S., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.04657 · Cited by 3
The trade-off between long-term memory and smoothness for recurrent networksPreprint
Ribeiro, A. H., Tiels, K., Aguirre, L. A., & Schön, T. B. (2019) · arXiv.org · doi:10.48550/arxiv.1906.08482 · Cited by 3
Yu, J., Zhang, C., Cheng, Y., et al. (2022) · ChemRxiv · doi:10.26434/chemrxiv-2022-0hl5p · Cited by 2
Ranković, B., Griffiths, R., Moss, H. B., & Schwaller, P. (2023) · ChemRxiv · doi:10.26434/chemrxiv-2022-nll2j-v3 · Cited by 2
MLLM-Tool: A Multimodal Large Language Model For Tool Agent LearningPreprint
Wang, C., Luo, W., Dong, S., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.10727 · Cited by 2
Multi-Task Inference: Can Large Language Models Follow Multiple Instructions at Once?Preprint
Son, G., Baek, S., Nam, S., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.11597 · Cited by 2
SciAgent: Tool-augmented Language Models for Scientific Reasoning
Ma, Y., Gou, Z., Hao, J., Xu, R., Wang, S., Pan, L., Yang, Y., Cao, Y., Sun, A., Awadalla, H., et al. (2024) · arXiv · doi:10.48550/arxiv.2402.11451 · Cited by 2
Liu, P., Tao, J., & Ren, Z. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.04119 · Cited by 1
Mixture-of-LoRAs: An Efficient Multitask Tuning for Large Language ModelsPreprint
Feng, W., Hao, C., Zhang, Y., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.03432 · Cited by 1
Instruction Multi-Constraint Molecular Generation Using a Teacher-Student Large Language ModelPreprint
Zhou, P., Wang, J., Li, C., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.13244 · Cited by 1
Transformers for molecular property prediction: Lessons learned from the past five yearsPreprint
Sultan, A., Sieg, J., Mathea, M., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.03969 · Cited by 1
Lee, C., Han, J., Ye, S., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.16418 · Cited by 1
Large Language Models as Molecular Design EnginesPreprint
Bhattacharya, D., Cassady, H. J., Hickner, M. A., et al. (2024) · ChemRxiv · doi:10.26434/chemrxiv-2024-n0l8q · Cited by 1
Human Readable Compression of GFA Paths Using Grammar-Based Code
Heringer, P., & Doerr, D. (2025) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.wabi.2025.14
OpenAI, Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., et al. (2023) · arXiv · doi:10.48550/arxiv.2303.08774
Kudo, T., & Richardson, J. (2018) · arXiv · doi:10.48550/arxiv.1808.06226
How Good is Your Tokenizer? On the Monolingual Performance of Multilingual Language Models
Rust, P., Pfeiffer, J., Vulić, I., Ruder, S., & Gurevych, I. (2020) · arXiv · doi:10.48550/arxiv.2012.15613
BiMediX: Bilingual Medical Mixture of Experts LLM
Pieri, S., Mullappilly, S. S., Khan, F. S., et al. (2024) · arXiv · doi:10.48550/arxiv.2402.13253
Crowdsourcing Multiple Choice Science Questions
Welbl, J., Liu, N. F., & Gardner, M. (2017) · arXiv · doi:10.48550/arxiv.1707.06209
Research works printed but not linked: 31
- Willett, 2011, Wiley Interdiscip. Rev.: Comput. Mol. Sci., 1, 46
- C.Hansch and A.Leo , Exploring QSAR.: Fundamentals and applications in chemistry and biology , American Chemical Society , 1995 , vol. 1
- Segler, 2018, ACS Cent. Sci., 4, 120, 10.1021/acscentsci.7b00512 · DOI · Paper page
- Prakash Dwivedi, 2023, J. Mach. Learn. Res., 24, 1
- Sanchez-Lengeling, 2021, Distill, 6, e33
- J.Gilmer , S. S.Schoenholz , P. F.Riley , O.Vinyals and E. D.George , Neural message passing for quantum chemistry , in International conference on machine learning , PMLR , 2017 , pp. 1263–1272
- V.Nair and G. E.Hinton , Rectified linear units improve restricted boltzmann machines , in Proceedings of the 27th international conference on machine learning , ICML-10 , 2010 , pp. 807–814
- Stiennon, 2020, Adv. Neural Inf. Process. Syst., 33, 3008
- T.Hayes , R.Rao , H.Akin , N. J.Sofroniew , D.Oktay , Z.Lin , R.Verkuil , V. Q.Tran , J.Deaton , M.Wiggert , R.Badkundri , I.Shafkat , J.Gong , A.Derry , R. S.Molina , N.Thomas , Y.Khan , C.Mishra , C.Kim , L. J.Bartie , M.Nemeth , P. D.Hsu , T.Sercu , S.Candido and A.Rives , bioRxiv , 2024 , preprint, 10.1101/2024.07.01.600583v2 , https://www.biorxiv.org/content/10.1101/2024.07.01.600583v2 · doi:10.1101/2024.07.01.600583v2
- Li, 2021, 2021, Proc. Int. Wirel. Commun. Mob. Comput. Conf., 1530, 10.1155/2021/7181815 · DOI
- A.Radford , K.Narasimhan , T.Salimans and I.Sutskever , Improving language understanding with unsupervised learning , 2018
- Hu, 2020, Adv. Neural Inf. Process. Syst., 33, 22118
- N.O'Boyle and A.Dalke , DeepSMILES: An Adaptation of SMILES for Use in Machine-Learning of Chemical Structures , ChemRxiv , 2018 , preprint
- D.Hendrycks , C.Burns , S.Basart , A.Zou , M.Mazeika , D.Song and J.Steinhardt , Measuring massive multitask language understanding , in International Conference on Learning Representations , 2020 , https://openreview.net/pdf?id=d7KBjmI3GmQ
- A.Pal , L.Kumar Umapathi and M.Sankarasubbu , MedMCQA: A large-scale multi-subject multi-choice dataset for medical domain question answering , in Conference on Health, Inference and Learning , PMLR , 2022 , pp. 248–260
- S.Wang , Y.Guo , Y.Wang , H.Sun and J.Huang , SMILES-BERT: Large Scale Unsupervised Pre-Training for Molecular Property Prediction , in Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB ’19 , Association for Computing Machinery , New York, NY, USA , 2019 , pp. 429–436 , 10.1145/3307339.3342186 · DOI · Paper page
- Ross, 2022, Nat. Mach. Intell., 4, 1256, 10.1038/s42256-022-00580-7 · DOI · Paper page
- J.Vig , Bertviz: A tool for visualizing multihead self-attention in the bert model , in ICLR workshop: Debugging machine learning models , 2019 , vol. 3
- Rong, 2020, Adv. Neural Inf. Process. Syst., 33, 12559
- M.Xu , X.Yuan , S.Miret and J.Tang , ProtST: Multi-modality learning of protein sequences and biomedical texts , in International Conference on Machine Learning , PMLR , 2023 , pp. 38749–38767
- C.-Y.Lin , ROUGE: A Package for Automatic Evaluation of Summaries , in Text Summarization Branches Out , Association for Computational Linguistics , Barcelona, Spain , 2004 , pp. 74–81 , https://aclanthology.org/W04-1013
- David, 2020, J. Cheminform., 12, 56, 10.1186/s13321-020-00460-5 · DOI · Paper page
- Lo, 2018, Drug Discovery Today, 23, 1538, 10.1016/j.drudis.2018.05.010 · DOI · Paper page
- Y.Liu , M.Ott , N.Goyal , J.Du , M.Joshi , D.Chen , O.Levy , M.Lewis , L.Zettlemoyer and V.Stoyanov , RoBERTa: A robustly optimized BERT pretraining approach , arXiv , 2019 , preprint, arXiv:1907.11692, 10.48550/arXiv.1907.11692 , http://arxiv.org/abs/1907.11692 · DOI · Paper page
- B. S.Bloom , Taxonomy of Educational Objectives: The Classification of Educational Goals; Handbook. Cognitive Domain , McKay , 1968
- S. S.Raman , V.Cohen , E.Rosen and I.Idrees , Planning with large language models via corrective re-prompting , Foundation Models , 2022 , https://openreview.net/pdf?id=cMDMRBe1TKs
- B.Ranković and P.Schwaller , BoChemian: Large language model embeddings for Bayesian optimization of chemical reactions , 2023 , https://openreview.net/pdf?id=A1RVn1m3J3
- Zheng, 2023, J. Am. Chem. Soc., 145, 18048, 10.1021/jacs.3c05819 · DOI · Paper page
- G.Landrum , Rdkit documentation, Release, 1(1-79):4 , 2013 , pp. 15333752 , https://media.readthedocs.org/pdf/rdkit/latest/rdkit.pdf
- Schwaller, 2021, Sci. Adv., 7, eabe4166, 10.1126/sciadv.abe4166 · DOI · Paper page
- O.Schilter , M.Alberts , F.Zipoli , A. C.Vaucher , P.Schwaller and T.Laino , Unveiling the secrets of 1H-NMR spectroscopy: A novel approach utilizing attention mechanisms , 2023 , https://openreview.net/pdf?id=4ilKwquW51
Cited by
From llm reasoning to autonomous ai agents: A comprehensive review
Ferrag, M. A., Tihanyi, N., & Debbah, M. (2026) · IEEE Access · doi:10.1109/access.2026.3698694 · Cited by 50
Tool learning with large language models: a survey
Qu, C., Dai, S., Wei, X., Cai, H., Wang, S., Yin, D., Xu, J., & Wen, J.-R. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-024-40678-2 · Cited by 99
From text to insight: large language models for chemical data extraction
Schilling-Wilhelmi, M., Ríos-García, M., Shabih, S., Gil, M. V., Miret, S., Koch, C. T., Márquez, J. A., & Jablonka, K. M. (2025) · Chemical Society Reviews · doi:10.1039/d4cs00913d · Cited by 142
Exploring the role of large language models in the scientific method: from hypothesis to discovery
Zhang, Y., Khan, S. A., Mahmud, A., Yang, H., Lavin, A., Levin, M. G., Frey, J. G., Dunnmon, J., Evans, J. A., Bundy, A., et al. (2025) · npj Artificial Intelligence · doi:10.1038/s44387-025-00019-5 · Cited by 241
Foundation models for materials discovery – current state and future directions
Pyzer‐Knapp, E. O., Manica, M., Staar, P., Morin, L., Ruch, P., Laino, T., Smith, J. R., & Curioni, A. (2025) · npj Computational Materials · doi:10.1038/s41524-025-01538-0 · Cited by 185
Metadata
- Authors
- Ramos, M. C., Collison, C. J., & White, A. D.
- Affiliations
- Future House, Inc. (US)
- Rochester Institute of Technology (US)
- Corresponding author
- White, Andrew D.
- Venue
- Chemical Science
- Publisher
- Royal Society of Chemistry (RSC)
- Published
- 2025
- Volume
- 16
- Issue
- 6
- Pages
- 2514-2572
- ISSN
- 2041-6520 (ISSN-L)
- 2041-6539
- PMC
- PMC11739813
- OpenAlex
- W4405185373
- Cited by
- 274
- References
- 516
- Citations by year
- 2026: 162 · 2025: 106
- FWCI
- 6.54
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- Locations
- Chemical Science (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Basic Energy Sciences (DE-SC0023354)
- Rochester Institute of Technology
- Topics
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Life Sciences › Pharmacology, Toxicology and Pharmaceutics › Drug Discovery › Computational Drug Discovery Methods
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- large language models, autonomous agents, chemistry, property prediction, synthesis planning, laboratory automation, model interpretability, LLM benchmark
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.
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.