Agentic workflows powered by large language models are beginning to assist chemists in literature search, summarization, and outline drafting. Though they remain unable to replace expert insight, these systems promise to reshape how reviews are prepared — shifting the human role from exhaustive curator to creative synthesizer, empowered by intelligent, always-on review-copilots.
This is a preview of subscription content, access via your institution
Relevant articles
Open Access articles citing this article.
-
Peer-reviewed by human experts: AI failed in key steps to generate a scoping review on the neural mechanisms of cross-education
European Journal of Applied Physiology Open Access 24 December 2025
Access options
Access Nature and 54 other Nature Portfolio journals
Get Nature+, our best-value online-access subscription
$32.99 / 30 days
cancel any time
Subscribe to this journal
Receive 12 digital issues and online access to articles
$119.00 per year
only $9.92 per issue
Buy this article
- Purchase on SpringerLink
- Instant access to the full article PDF.
USD 39.95
Prices may be subject to local taxes which are calculated during checkout
References
Caldas Ramos, M., Collison, C. J. & White, A. D. A review of large language models and autonomous agents in chemistry. Chem. Sci. 16, 2514–2572 (2025).
Boiko, D. A., MacKnight, R., Kline, B. & Gomes, G. Autonomous chemical research with large language models. Nature 624, 570–578 (2023).
Lála, J. et al. PaperQA: Retrieval-augmented generative agent for scientific research. Preprint at https://arxiv.org/abs/2312.07559 (2023).
Bran, A. M. et al. Augmenting large language models with chemistry tools. Nat. Mach. Intell. 6, 525–535 (2024).
Zheng, Z. et al. Large language models for reticular chemistry. Nat. Rev. Mater. 10, 369–381 (2025).
Huang, J. & Tan, M. The role of ChatGPT in scientific communication: writing better scientific review articles. Am. J. Cancer Res. 13, 1148–1154 (2023).
Shao, Y. et al. Assisting in writing Wikipedia-like articles from scratch with large language models. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1: Long Papers, 6252–6278 (Association for Computational Linguistics, 2024).
Gibb, B. C. Eric the AI research assistant for chemists. Nat. Chem. 17, 157–158 (2025).
How to write an excellent Review article. Nat. Rev. Bioeng. 2, 907–907 (2024).
Mishra, T. et al. Use of large language models as artificial intelligence tools in academic research and publishing among global clinical researchers. Sci. Rep. 14, 31672 (2024).
Acknowledgements
Z.Z. extends special gratitude to J. Weng from OpenAI and K. Dong from Stanford University for valuable discussions.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Competing interests
The author declares no competing interests.
Rights and permissions
About this article
Cite this article
Zheng, Z. The future of reviews writing in the AI era. Nat Rev Chem 9, 495–496 (2025). https://doi.org/10.1038/s41570-025-00738-y
Published:
Version of record:
Issue date:
DOI: https://doi.org/10.1038/s41570-025-00738-y
This article is cited by
-
Peer-reviewed by human experts: AI failed in key steps to generate a scoping review on the neural mechanisms of cross-education
European Journal of Applied Physiology (2025)
