Elamur Research⌕
☰
home / papers / 2026 / A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization

A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization

Paper · 2026 · Ziqing Wang, Kexin Zhang, Zihan Zhao et al.

Summary

This survey reviews how large language models are used to design molecules from text instructions. It covers two tasks: generating new molecules from scratch and editing an existing molecule to improve its properties. The authors limit the scope to models with over 1B parameters that directly output molecular structures. Tool-orchestrating systems and smaller chemical language models are excluded.

The survey is organised around four evaluation challenges: chemical validity, synthesizability, property control and structural diversity. Methods are grouped by learning paradigm rather than architecture. Untuned approaches include zero-shot prompting and in-context learning; tuned approaches include supervised fine-tuning and preference tuning. The authors also catalogue datasets, benchmarks and metrics.

Their main finding is that every paradigm involves trade-offs:

  • Prompting is flexible but weak on validity.
  • Fine-tuning secures validity and property control but tends to lose diversity.
  • Preference tuning helps diversity.

Synthesizability is the least solved problem across all methods. This matters because valid-looking molecules may be impossible to make in a lab. The paper offers a structured map of the field for NLP and chemistry researchers.

Key points

  • The taxonomy (Fig. 1) assigns representative systems to each paradigm:
    • Generation: MolReGPT and LLM4GraphGen (in-context learning); LlaSMol, ChemLLM, Mol-instructions and mCLM (fine-tuning); SmileyLLama and Mol-MOE (preference tuning).
    • Optimization: MOLLEO (zero-shot); ChatDrug (in-context learning); DrugAssist and GeLLM³O (fine-tuning); POLO and NatureLM (preference tuning).
  • Inclusion criteria: at least 1B parameters, and the LLM must act as the molecule generator rather than as a feature extractor or controller.
  • The authors argue that existing benchmarks such as MOSES and GuacaMol were not built for LLMs. They call for a unified benchmark with leakage-safe splits, instruction-following and robustness metrics, and a live leaderboard.
  • Proposed future directions:
    • treating synthesizability as a constraint during generation, e.g. through retrosynthesis and reward penalties;
    • multi-modal reasoning over SMILES, 2D graphs and 3D conformations;
    • standardised evaluation.
  • As an impact example, mCLM proposed edits reducing drug-induced liver injury for two failed drug candidates, Evobrutinib and TNG348. A maintained reading list is available on GitHub (REAL-Lab-NU/Awesome-LLM-Centric-Molecular-Discovery).

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Fields, topics and concepts

📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 worksComputational Theory and Mathematics · 252 worksMaterials Science · 26 worksMaterials Chemistry · 26 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu and Kaize Ding. 2026. A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.2026

@inproceedings{wang2026survey,
  title = {{A Survey of Large Language Models for Text-Guided Molecular Discovery: From Molecule Generation to Optimization}},
  author = {Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu and Kaize Ding},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.2026},
  url = {https://doi.org/10.18653/v1/2026.acl-long.2026}
}

References

144 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dhruv Agarwal, Manoj Ghuhan Arivazhagan, Rajarshi Das, Sandesh Swamy, Sopan Khosla, and Rashmi Gangadharaiah. 2025. Searching for optimal solutions with llms via bayesian optimization. In The Thirteenth International Conference on Learning Representations. find
  2. Evan R Antoniuk, Shehtab Zaman, Tal Ben-Nun, Peggy Li, James Diffenderfer, Busra Demirci, Obadiah Smolenski, Tim Hsu, Anna M Hiszpanski, Kenneth Chiu, and 1 others. 2025. Boom: Benchmarking out-of-distribution molecular property predictions of machine learning models. arXiv preprint arXiv:2505.01912… — [arXiv:2505.01912](https://arxiv.org/abs/2505.01912) find
  3. Viraj Bagal, Rishal Aggarwal, PK Vinod, and U Deva Priyakumar. 2021. Molgpt: molecular generation using a transformer-decoder model. Journal of chemical information and modeling, 62(9):2064–2076. find
  4. Menua Bedrosian, Philipp Guevorguian, Tigran Fahradyan, Gayane Chilingaryan, Hrant Khachatrian, and Armen Aghajanyan. 2024. Small molecule optimization with large language models. In Neurips 2024 Workshop Foundation Models for Science: Progress, Opportunities, and Challenges. find
  5. Mostapha Benhenda. 2017. Chemgan challenge for drug discovery: can ai reproduce natural chemical diversity? arXiv preprint arXiv:1708.08227. — [arXiv:1708.08227](https://arxiv.org/abs/1708.08227) find
  6. Debjyoti Bhattacharya, Harrison J Cassady, Michael A Hickner, and Wesley F Reinhart. 2024. Large language models as molecular design engines. Journal of Chemical Information and Modeling, 64(18):7086– 7096. find
  7. GR Bickerton, GV Paolini, J Besnard, S Muresan, and AL Hopkins. 2012. Quantifying the chemical beauty of drugs. Nature Chemistry, 4(2):90–98. find
  8. Nathan Brown, Marco Fiscato, Marwin HS Segler, and Alain C Vaucher. 2019. Guacamol: Benchmarking models for de novo molecular design. Journal of chemical information and modeling, 59(3):1096– 1108. find
  9. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, and 1 others. 2020. Language models are few-shot learners. NeurIPS, 33:1877–1901.
  10. Diego Calanzone, Pierluca D’Oro, and Pierre-Luc Bacon. 2025. Mol-moe: Training preference-guided routers for molecule generation. arXiv preprint arXiv:2502.05633. — [arXiv:2502.05633](https://arxiv.org/abs/2502.05633) find
  11. Joseph M Cavanagh, Kunyang Sun, Andrew Gritsevskiy, Dorian Bagni, Thomas D Bannister, and Teresa Head-Gordon. 2024. Smileyllama: Modifying large language models for directed chemical space exploration. arXiv preprint arXiv:2409.02231. — [arXiv:2409.02231](https://arxiv.org/abs/2409.02231) find
  12. Angelica Chen, Samuel D. Stanton, Frances Ding, Robert G. Alberstein, Andrew M. Watkins, Richard Bonneau, Vladimir Gligorijević, Kyunghyun Cho, and Nathan C. Frey. 2025. Generalists vs. specialists: Evaluating llms on highly-constrained biophysical sequence optimization tasks. find
  13. Yu Cheng, Yongshun Gong, Yuansheng Liu, Bosheng Song, and Quan Zou. 2021. Molecular design in drug discovery: a comprehensive review of deep generative models. Briefings in bioinformatics, 22(6):bbab344. find
  14. Connor W Coley, Luke Rogers, William H Green, and Klavs F Jensen. 2018. Scscore: synthetic complexity learned from a reaction corpus. Journal of chemical information and modeling, 58(2):252–261. find
  15. Connor W Coley, Dale A Thomas III, Justin AM Lummiss, Jonathan N Jaworski, Christopher P Breen, Victor Schultz, Travis Hart, Joshua S Fishman, Luke Rogers, Hanyu Gao, and 1 others. 2019. A robotic platform for flow synthesis of organic compounds informed by ai planning. Science, 365(6453):eaax1566. find
  16. Zhilian Dai, Jie Zhang, Songyou Zhong, Jiawei Fu, Yangyang Deng, Dan Zhang, Yichao Liu, and Peng Gao. 2025. A zero-shot single-point molecule optimization model: Mimicking medicinal chemists’ expertise. find
  17. Nicola De Cao and Thomas Kipf. 2018. Molgan: An implicit generative model for small molecular graphs. arXiv preprint arXiv:1805.11973. — [arXiv:1805.11973](https://arxiv.org/abs/1805.11973) find
  18. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies,…
  19. Vishal Dey, Xiao Hu, and Xia Ning. 2025. Gellm3 o: Generalizing large language models for multi-property molecule optimization. arXiv preprint arXiv:2502.13398. — [arXiv:2502.13398](https://arxiv.org/abs/2502.13398) find
  20. JL Durant, BA Leland, DR Henry, and JG Nourse. 2002. Reoptimization of mdl keys for use in drug discovery. Journal of Chemical Information and Computer Sciences, 42(6):1273–1280. find
  21. Carl Edwards, Chi Han, Gawon Lee, Thao Nguyen, Sara Szymkuć, Chetan Kumar Prasad, Bowen Jin, Jiawei Han, Ying Diao, Ge Liu, Hao Peng, Bartosz A. Grzybowski, Martin D. Burke, and Heng Ji. 2026. mCLM: A modular chemical language model that generates functional and makeable molecules. In International… find
  22. Carl Edwards, Tuan Lai, Kevin Ros, Garrett Honke, Kyunghyun Cho, and Heng Ji. 2022. Translation between molecules and natural language. arXiv preprint arXiv:2204.11817.
  23. Carl Edwards, Qingyun Wang, Lawrence Zhao, and Heng Ji. 2024. L+ m-24: Building a dataset for language+ molecules@ acl 2024. arXiv preprint arXiv:2403.00791. find
  24. Carl Edwards, ChengXiang Zhai, and Heng Ji. 2021. Text2mol: Cross-modal molecule retrieval with natural language queries. In EMNLP, pages 595–607.
  25. Daniel C Elton, Zois Boukouvalas, Mark D Fuge, and Peter W Chung. 2019. Deep learning for molecular design—a review of the state of the art. Molecular Systems Design & Engineering, 4(4):828–849. find
  26. Peter Ertl, Bernhard Rohde, and Paul Selzer. 2000. Fast calculation of molecular polar surface area as a sum of fragment-based contributions and its application to the prediction of drug transport properties. Journal of Medicinal Chemistry, 43(20):3714–3717. find
  27. Peter Ertl and Ansgar Schuffenhauer. 2009. Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. Journal of Cheminformatics, 1(1):8. find
  28. Chuanliu Fan, Ziqiang Cao, Zicheng Ma, Nan Yu, Yimin Peng, Jun Zhang, Yiqin Gao, and Guohong Fu. 2025. Chatmol: A versatile molecule designer based on the numerically enhanced large language model. arXiv preprint arXiv:2502.19794. — [arXiv:2502.19794](https://arxiv.org/abs/2502.19794) find
  29. Yin Fang, Xiaozhuan Liang, Ningyu Zhang, Kangwei Liu, Rui Huang, Zhuo Chen, Xiaohui Fan, and Huajun Chen. 2023. Mol-instructions: A large-scale biomolecular instruction dataset for large language models. arXiv preprint arXiv:2306.08018. find
  30. Henri A Favre and Warren H Powell. 2014. Nomenclature of Organic Chemistry: IUPAC Recommendations and Preferred Names 2013. Royal Society of Chemistry. find
  31. Paul G Francoeur, Tomohide Masuda, Jocelyn Sunseri, Andrew Jia, Richard B Iovanisci, Ian Snyder, and David R Koes. 2020. Three-dimensional convolutional neural networks and a cross-docked data set for structure-based drug design. Journal of chemical information and modeling, 60(9):4200–4215. find
  32. Veronika Ganeeva, Andrey Sakhovskiy, Kuzma Khrabrov, Andrey Savchenko, Artur Kadurin, and Elena Tutubalina. 2024. Lost in translation: Chemical language models and the misunderstanding of molecule structures. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 12994–13013… find
  33. Bowen Gao, Yanwen Huang, Yiqiao Liu, Wenxuan Xie, Wei-Ying Ma, Ya-Qin Zhang, and Yanyan Lan. 2025. Pushing the boundaries of structure-based drug design through collaboration with large language models. arXiv preprint arXiv:2503.01376. — [arXiv:2503.01376](https://arxiv.org/abs/2503.01376) find
  34. Wenhao Gao and Connor W Coley. 2020. The synthesizability of molecules proposed by generative models. Journal of chemical information and modeling, 60(12):5714–5723. find
  35. Miguel García-Ortegón, Gregor NC Simm, Austin J Tripp, José Miguel Hernández-Lobato, Andreas Bender, and Sergio Bacallado. 2022. Dockstring: easy molecular docking yields better benchmarks for ligand design. Journal of chemical information and modeling, 62(15):3486–3502. find
  36. Anna Gaulton, Louisa J Bellis, A Patricia Bento, Jon Chambers, Mark Davies, Anne Hersey, Yvonne Light, Shaun McGlinchey, David Michalovich, Bissan Al-Lazikani, and 1 others. 2012. Chembl: a large-scale bioactivity database for drug discovery. Nucleic acids research, 40(D1):D1100–D1107. find
  37. Samuel Genheden, Amol Thakkar, Veronika Chadi-mová, Jean-Louis Reymond, Ola Engkvist, and Esben Bjerrum. 2020. Aizynthfinder: a fast, robust and flexible open-source software for retrosynthetic planning. Journal of cheminformatics, 12(1):70. find
  38. Dimitris Gkoumas. 2024. Almol: Aligned language-molecule translation llms through offline preference contrastive optimisation. arXiv preprint arXiv:2405.08619. find
  39. Dimitris Gkoumas and Maria Liakata. 2024. Less for more: Enhanced feedback-aligned mixed llms for molecule caption generation and fine-grained nli evaluation. arXiv preprint arXiv:2405.13984. find
  40. Rafael Gómez-Bombarelli, Jennifer N Wei, David Duvenaud, José Miguel Hernández-Lobato, Benjamín Sánchez-Lengeling, Dennis Sheberla, Jorge Aguilera-Iparraguirre, Timothy D Hirzel, Ryan P Adams, and Alán Aspuru-Guzik. 2018. Automatic chemical design using a data-driven continuous representation of mol… find
  41. Daniele Grandi, Yash Patawari Jain, Allin Groom, Brandon Cramer, and Christopher McComb. 2025. Evaluating large language models for material selection. Journal of Computing and Information Science in Engineering, 25(2):021004. find
  42. Huijie Guo, Xudong Xing, Yongjie Zhou, Wenjiao Jiang, Xiaoyi Chen, Ting Wang, Zixuan Jiang, Yibing Wang, Junyan Hou, Yukun Jiang, and 1 others. 2025. A survey of large language model for drug research and development. IEEE Access. find
  43. Corwin Hansch, John E Quinlan, and Gary L Lawrence. 1968. Linear free-energy relationship between partition coefficients and the aqueous solubility of organic liquids. The journal of organic chemistry, 33(1):347– 350. find
  44. Weihua Hu, Matthias Fey, Marinka Zitnik, Yuxiao Dong, Hongyu Ren, Bowen Liu, Michele Catasta, and Jure Leskovec. 2020. Open graph benchmark: Datasets for machine learning on graphs. Advances in neural information processing systems, 33:22118–22133. find
  45. Kexin Huang, Tianfan Fu, Wenhao Gao, Yue Zhao, Yusuf Roohani, Jure Leskovec, Connor W Coley, Cao Xiao, Jimeng Sun, and Marinka Zitnik. 2021. Therapeutics data commons: Machine learning datasets and tasks for drug discovery and development. arXiv preprint arXiv:2102.09548. find
  46. John J Irwin, Teague Sterling, Michael M Mysinger, Erin S Bolstad, and Ryan G Coleman. 2012. Zinc: a free tool to discover chemistry for biology. Journal of chemical information and modeling, 52(7):1757– 1768. find
  47. Nikita Janakarajan, Tim Erdmann, Sarath Swaminathan, Teodoro Laino, and Jannis Born. 2024. Language models in molecular discovery. In Drug Development Supported by Informatics, pages 121–141. Springer. find
  48. Hyosoon Jang, Yunhui Jang, Jaehyung Kim, and Sungsoo Ahn. 2024. Can llms generate diverse molecules? towards alignment with structural diversity. arXiv preprint arXiv:2410.03138. — [arXiv:2410.03138](https://arxiv.org/abs/2410.03138) find
  49. Wengong Jin, Regina Barzilay, and Tommi Jaakkola. 2018. Junction tree variational autoencoder for molecular graph generation. In International conference on machine learning, pages 2323–2332. PMLR. find
  50. Wengong Jin, Regina Barzilay, and Tommi Jaakkola. 2020. Multi-objective molecule generation using interpretable substructures. In International Conference on Machine Learning, pages 4849–4859. PMLR. find
  51. Sunghwan Kim, Jie Chen, Tiejun Cheng, Asta Gindulyte, Jia He, Siqian He, Qingliang Li, Benjamin A Shoemaker, Paul A Thiessen, Bo Yu, and 1 others. 2019. find
  52. Pubchem 2019 update: improved access to chemical data. Nucleic acids research, 47(D1):D1102–D1109. find
  53. Sunghwan Kim, Jie Chen, Tiejun Cheng, Asta Gindulyte, Jia He, Siqian He, Qingliang Li, Benjamin A Shoemaker, Paul A Thiessen, Bo Yu, and 1 others. 2025. find
  54. Pubchem 2025 update. Nucleic Acids Research, 53(D1):D1516–D1525. find
  55. Sunghwan Kim, Paul A Thiessen, Evan E Bolton, Jie Chen, Gang Fu, Asta Gindulyte, Lianyi Han, Jane He, Siqian He, Benjamin A Shoemaker, and 1 others. 2016. Pubchem substance and compound databases. Nucleic acids research, 44(D1):D1202–D1213. find
  56. Tobias Kreiman and Aditi S Krishnapriyan. 2025. Understanding and mitigating distribution shifts for machine learning force fields. arXiv preprint arXiv:2503.08674. — [arXiv:2503.08674](https://arxiv.org/abs/2503.08674) find
  57. Mario Krenn, Florian Häse, AkshatKumar Nigam, Pascal Friederich, and Alan Aspuru-Guzik. 2020. Self-referencing embedded strings (selfies): A 100% robust molecular string representation. Machine Learning: Science and Technology, 1(4):045024. find
  58. Greg Landrum and 1 others. 2013. Rdkit: A software suite for cheminformatics, computational chemistry, and predictive modeling. Greg Landrum, 8(31.10):5281. find
  59. Khiem Le and Nitesh V Chawla. 2024. Utilizing large language models in an iterative paradigm with domain feedback for molecule optimization. arXiv preprint arXiv:2410.13147. — [arXiv:2410.13147](https://arxiv.org/abs/2410.13147) find
  60. Khiem Le, Zhichun Guo, Kaiwen Dong, Xiaobao Huang, Bozhao Nan, Roshni Iyer, Xiangliang Zhang, Olaf Wiest, Wei Wang, and Nitesh V Chawla. 2024. Molx: Enhancing large language models for molecular learning with a multi-modal extension. arXiv preprint arXiv:2406.06777. — [arXiv:2406.06777](https://arxiv.org/abs/2406.06777) find
  61. Chanhui Lee, Yuheon Song, YongJun Jeong, Hanbum Ko, Rodrigo Hormazabal, Sehui Han, Kyunghoon Bae, Sungbin Lim, and Sungwoong Kim. 2025. Mol-llm: Generalist molecular llm with improved graph utilization. arXiv preprint arXiv:2502.02810. — [arXiv:2502.02810](https://arxiv.org/abs/2502.02810) find
  62. Vladimir I Levenshtein. 1966. Binary codes capable of correcting deletions, insertions, and reversals. Soviet physics doklady, 10(8):707–710. find
  63. Jiatong Li, Yunqing Liu, Wenqi Fan, Xiao-Yong Wei, Hui Liu, Jiliang Tang, and Qing Li. 2024c. Empowering molecule discovery for molecule-caption translation with large language models: A chatgpt perspective. IEEE transactions on knowledge and data engineering. find
  64. Jiatong Li, Yunqing Liu, Wei Liu, Jingdi Le, Di Zhang, Wenqi Fan, Dongzhan Zhou, Yuqiang Li, and Qing Li. 2024d. Molreflect: Towards in-context fine-grained alignments between molecules and texts. arXiv preprint arXiv:2411.14721. — [arXiv:2411.14721](https://arxiv.org/abs/2411.14721) find
  65. Chang Liao, Yemin Yu, Yu Mei, and Ying Wei. 2024. From words to molecules: A survey of large language models in chemistry. arXiv preprint arXiv:2402.01439. — [arXiv:2402.01439](https://arxiv.org/abs/2402.01439) find
  66. Xiaohan Lin, Yijie Xia, Yupeng Huang, Shuo Liu, Jun Zhang, and Yi Qin Gao. 2024. Versatile molecular editing via multimodal and group-optimized generative learning. find
  67. Xuan Lin, Long Chen, Yile Wang, Xiangxiang Zeng, and Philip S. Yu. 2025. Property enhanced instruction tuning for multi-task molecule generation with large language models. arXiv preprint arXiv:2412.18084. — [arXiv:2412.18084](https://arxiv.org/abs/2412.18084) find
  68. Gang Liu, Michael Sun, Wojciech Matusik, Meng Jiang, and Jie Chen. 2024a. Multimodal large language models for inverse molecular design with retrosynthetic planning. arXiv preprint arXiv:2410.04223. — [arXiv:2410.04223](https://arxiv.org/abs/2410.04223) find
  69. Shengchao Liu, Weili Nie, Chengpeng Wang, Jiarui Lu, Zhuoran Qiao, Ling Liu, Jian Tang, Chaowei Xiao, and Anima Anandkumar. 2022. Multi-modal molecule structure-text model for text-based retrieval and editing. arXiv preprint arXiv:2212.10789. find
  70. Shengchao Liu, Weili Nie, Chengpeng Wang, Jiarui Lu, Zhuoran Qiao, Ling Liu, Jian Tang, Chaowei Xiao, and Animashree Anandkumar. 2023. Multimodal molecule structure–text model for text-based retrieval and editing. Nature Machine Intelligence, 5(12):1447–1457. find
  71. Shengchao Liu, Jiongxiao Wang, Yijin Yang, Chengpeng Wang, Ling Liu, Hongyu Guo, and Chaowei Xiao. 2024b. Conversational drug editing using retrieval and domain feedback. In The twelfth international conference on learning representations. find
  72. Jiatong Li, Junxian Li, Yunqing Liu, Dongzhan Zhou, and Qing Li. 2024a. Tomg-bench: Evaluating llms on text-based open molecule generation. arXiv preprint arXiv:2412.14642. — [arXiv:2412.14642](https://arxiv.org/abs/2412.14642) find
  73. Xianggen Liu, Yan Guo, Haoran Li, Jin Liu, Shudong Huang, Bowen Ke, and Jiancheng Lv. 2024c. Drugllm: Open large language model for few-shot molecule generation. arXiv preprint arXiv:2405.06690. — [arXiv:2405.06690](https://arxiv.org/abs/2405.06690) find
  74. Jiatong Li, Wei Liu, Zhihao Ding, Wenqi Fan, Yuqiang Li, and Qing Li. 2024b. Large language models are in-context molecule learners. arXiv preprint arXiv:2403.04197. — [arXiv:2403.04197](https://arxiv.org/abs/2403.04197) find
  75. Xuefeng Liu, Songhao Jiang, Bo Li, and Rick Stevens. 2025. Controllablegpt: A ground-up designed controllable gpt for molecule optimization. arXiv preprint arXiv:2502.10631. — [arXiv:2502.10631](https://arxiv.org/abs/2502.10631) find
  76. Hannes H Loeffler, Jiazhen He, Alessandro Tibo, Jon Paul Janet, Alexey Voronov, Lewis H Mervin, and Ola Engkvist. 2024. Reinvent 4: Modern ai– driven generative molecule design. Journal of Cheminformatics, 16(1):20. find
  77. Hao Lu, Zhiqiang Wei, Xuze Wang, Kun Zhang, and Hao Liu. 2023. Graphgpt: A graph enhanced generative pretrained transformer for conditioned molecular generation. International Journal of Molecular Sciences, 24(23):16761. find
  78. Jieyu Lu, Zhangde Song, Qiyuan Zhao, Yuanqi Du, Yirui Cao, Haojun Jia, and Chenru Duan. 2024. Generative design of functional metal complexes utilizing the internal knowledge of large language models. arXiv preprint arXiv:2410.18136. — [arXiv:2410.18136](https://arxiv.org/abs/2410.18136) find
  79. Andres M. Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D White, and Philippe Schwaller. 2024. Augmenting large language models with chemistry tools. Nature Machine Intelligence, 6(5):525– 535. find
  80. Gabriel A Pinheiro, Johnatan Mucelini, Marinalva D Soares, Ronaldo C Prati, Juarez LF Da Silva, and Marcos G Quiles. 2020. Machine learning prediction of nine molecular properties based on the smiles representation of the qm9 quantum-chemistry dataset. The Journal of Physical Chemistry A, 124(47):98… find
  81. Jonathan Pirnay, Jan G Rittig, Alexander B Wolf, Martin Grohe, Jakob Burger, Alexander Mitsos, and Dominik G Grimm. 2025. Graphxform: graph transformer for computer-aided molecular design. Digital Discovery, 4(4):1052–1065. find
  82. Daniil Polykovskiy, Alexander Zhebrak, Benjamin Sanchez-Lengeling, Sergey Golovanov, Oktai Tatanov, Stanislav Belyaev, Rauf Kurbanov, Aleksey Artamonov, Vladimir Aladinskiy, Mark Veselov, and 1 others. 2020. Molecular sets (moses): a benchmarking platform for molecular generation models. Frontiers i… find
  83. A Mirza, N Alampara, S Kunchapu, B Emoekabu, A Krishnan, M Wilhelmi, M Okereke, J Eberhardt, AM Elahi, M Greiner, and 1 others. 2024a. Are large language models superhuman chemists? arXiv preprint arXiv:2404.01475. — [arXiv:2404.01475](https://arxiv.org/abs/2404.01475) find
  84. Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. Squad: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250.
  85. Adrian Mirza, Nawaf Alampara, Sreekanth Kunchapu, Martiño Ríos-García, Benedict Emoekabu, Aswanth Krishnan, Tanya Gupta, Mara Schilling-Wilhelmi, Macjonathan Okereke, Anagha Aneesh, and 1 others. 2024b. Are large language models superhuman chemists? arXiv preprint arXiv:2404.01475. — [arXiv:2404.01475](https://arxiv.org/abs/2404.01475) find
  86. Mayk Caldas Ramos, Christopher J. Collison, and Andrew D. White. 2025. A review of large language models and autonomous agents in chemistry. Chemical Science.
  87. HL Morgan. 1965. The generation of a unique machine description for chemical structures—a technique developed at chemical abstracts service. Journal of Chemical Documentation, 5(2):107–113. find
  88. Shogo Nakamura, Nobuaki Yasuo, and Masakazu Sek-ijima. 2025. Molecular optimization using a conditional transformer for reaction-aware compound exploration with reinforcement learning. Communications Chemistry, 8(1):40. find
  89. Noel M O’Boyle, Michael Banck, Craig A James, Chris Morley, Tim Vandermeersch, and Geoffrey R Hutchison. 2011. Open babel: An open chemical toolbox. Journal of cheminformatics, 3(1):33. find
  90. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
  91. Vilfredo Pareto. 1919. Manuale di economia politica con una introduzione alla scienza sociale, volume 13. Società editrice libraria. find
  92. Jinyeong Park, Jaegyoon Ahn, Jonghwan Choi, and Jibum Kim. 2025. Mol-air: Molecular reinforcement learning with adaptive intrinsic rewards for goal-directed molecular generation. Journal of Chemical Information and Modeling, 65(5):2283–2296. find
  93. Nian Ran, Yue Wang, and Richard Allmendinger. 2025. MOLLM: multi-objective large language model for molecular design - optimizing with experts. arXiv preprint arXiv:2502.12845. — [arXiv:2502.12845](https://arxiv.org/abs/2502.12845) find
  94. Oscar Rivera, Ziqing Wang, Matthieu Dagommer, Abhishek Pandey, and Kaize Ding. 2026. Glass-mol: Interpretable molecular property prediction with concept bottleneck models. arXiv preprint arXiv:2603.01274. — [arXiv:2603.01274](https://arxiv.org/abs/2603.01274) find
  95. Jerret Ross, Brian Belgodere, Vijil Chenthamarakshan, Inkit Padhi, Youssef Mroueh, and Payel Das. 2022. Large-scale chemical language representations capture molecular structure and properties. Nature Machine Intelligence, 4(12):1256–1264. find
  96. Jerret Ross, Samuel Hoffman, Brian Belgodere, Vijil Chenthamarakshan, Youssef Mroueh, and Payel Das. 2024. Learning to optimize molecules with a chemical language model. In Annual Conference on Neural Information Processing Systems. find
  97. Henry W Sprueill, Carl Edwards, Khushbu Agarwal, Mariefel V Olarte, Udishnu Sanyal, Conrad Johnston, Hongbin Liu, Heng Ji, and Sutanay Choudhury. 2024. Chemreasoner: Heuristic search over a large language model’s knowledge space using quantum-chemical feedback. arXiv preprint arXiv:2402.10980. find
  98. Sakhinana Sagar Srinivas and Venkataramana Runkana. 2024. Crossing new frontiers: Knowledge-augmented large language model prompting for zero-shot text-based de novo molecule design. arXiv preprint arXiv:2408.11866. — [arXiv:2408.11866](https://arxiv.org/abs/2408.11866) find
  99. Kunyang Sun, Dorian Bagni, Joseph M Cavanagh, Yingze Wang, Jacob M Sawyer, Andrew Gritsevskiy, Oufan Zhang, and Teresa Head-Gordon. 2025. Synllama: Generating synthesizable molecules and their analogs with large language models. arXiv preprint arXiv:2503.12602. — [arXiv:2503.12602](https://arxiv.org/abs/2503.12602) find
  100. Richard S Sutton, Andrew G Barto, and 1 others. 1998. Reinforcement learning: An introduction, volume 1. MIT press Cambridge. find
  101. Ziqing Wang and Kaize Ding. 2018. Remol: Llm-guided molecular optimization with reinforcement learning. find
  102. Ziqing Wang, Chengsheng Mao, Xiaole Wen, Yuan Luo, and Kaize Ding. 2025b. Amanda: Agentic medical knowledge augmentation for data-efficient medical visual question answering. arXiv preprint arXiv:2510.02328. find
  103. Ziqing Wang, Yibo Wen, Abhishek Pandy, Han Liu, and Kaize Ding. 2026. Molmem: Memory-augmented agentic reinforcement learning for sample-efficient molecular optimization. arXiv preprint arXiv:2604.12237. find
  104. Xiangru Tang, Howard Dai, Elizabeth Knight, Fang Wu, Yunyang Li, Tianxiao Li, and Mark Gerstein. 2024. A survey of generative ai for de novo drug design: new frontiers in molecule and protein generation. Briefings in Bioinformatics, 25(4):bbae338. find
  105. Ziqing Wang, Yibo Wen, William Pattie, Xiao Luo, Weimin Wu, Jerry Yao-Chieh Hu, Abhishek Pandey, Han Liu, and Kaize Ding. 2025c. Polo: Preference-guided multi-turn reinforcement learning for lead optimization. arXiv preprint arXiv:2509.21737. — [arXiv:2509.21737](https://arxiv.org/abs/2509.21737) find
  106. Wen Tao, Jing Tang, Alvin Chan, Bryan Hooi, Baolong Bi, Nanyun Peng, Yuansheng Liu, and Yiwei Wang. 2025. How to make large language models generate 100% valid molecules? In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 26576–26591. find
  107. Jason Wei, Yi Tay, Rishi Bommasani, Colin Raffel, Barret Zoph, Sebastian Borgeaud, Dani Yogatama, Maarten Bosma, Denny Zhou, Donald Metzler, and 1 others. 2022a. Emergent abilities of large language models. TMLR.
  108. Morgan Thomas, Noel M O’Boyle, Andreas Bender, and Chris De Graaf. 2024. Molscore: a scoring, evaluation and benchmarking framework for generative models in de novo drug design. Journal of Cheminformatics, 16(1):64. find
  109. Prudencio Tossou, Cas Wognum, Michael Craig, Hadrien Mary, and Emmanuel Noutahi. 2024. Real-world molecular out-of-distribution: Specification and investigation. Journal of Chemical Information and Modeling, 64(3):697–711. find
  110. Clement Vignac, Igor Krawczuk, Antoine Siraudin, Bohan Wang, Volkan Cevher, and Pascal Frossard. 2022. Digress: Discrete denoising diffusion for graph generation. arXiv preprint arXiv:2209.14734. — [arXiv:2209.14734](https://arxiv.org/abs/2209.14734) find
  111. Pat Walters. 2024. Silly things large language models do when generating molecules. Practical Cheminformatics Blog. https://practicalcheminformati cs.blogspot.com/2024/10/silly-things-lar ge-language-models-do.html. find
  112. Haorui Wang, Marta Skreta, Cher Tian Ser, Wenhao Gao, Lingkai Kong, Felix Strieth-Kalthoff, Chenru Duan, Yuchen Zhuang, Yue Yu, Yanqiao Zhu, Yuanqi Du, Alan Aspuru-Guzik, Kirill Neklyudov, and Chao Zhang. 2025a. Efficient evolutionary search over chemical space with large language models. In The Thi… find
  113. Y. Wang, H. Zhao, S. Sciabola, and W. Wang. 2023. cmolgpt: A conditional generative pre-trained transformer for target-specific de novo molecular generation. Molecules, 28(11):4430. find
  114. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022b. Chain-of-thought prompting elicits reasoning in large language models. NeurIPS, 35:24824–24837.
  115. David Weininger. 1988. Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. Journal of chemical information and computer sciences, 28(1):31–36. find
  116. Gaoqi Weng, Huifeng Zhao, Dou Nie, Haotian Zhang, Liwei Liu, Tingjun Hou, and Yu Kang. 2024. Redis-cmol: Benchmarking molecular generation models in biological properties. Journal of Medicinal Chemistry, 67(2):1533–1543. find
  117. Egon L Willighagen, John W Mayfield, Jonathan Alvars-son, Arvid Berg, Lars Carlsson, Nina Jeliazkova, Stefan Kuhn, Tomáš Pluskal, Miquel Rojas-Chertó, Ola Spjuth, and 1 others. 2017. The chemistry development kit (cdk) v2. 0: atom typing, depiction, molecular formulas, and substructure searching. Jo… find
  118. Shirley Wu, Kaidi Cao, Bruno Ribeiro, James Zou, and Jure Leskovec. 2024a. Graphmetro: Mitigating complex graph distribution shifts via mixture of aligned experts. Advances in Neural Information Processing Systems, 37:9358–9387. find
  119. Zhenqin Wu, Bharath Ramsundar, Evan N Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S Pappu, Karl Leswing, and Vijay Pande. 2018. Moleculenet: a benchmark for molecular machine learning. Chemical science, 9(2):513–530. find
  120. Zhenxing Wu, Odin Zhang, Xiaorui Wang, Li Fu, Huifeng Zhao, Jike Wang, Hongyan Du, Dejun Jiang, Yafeng Deng, Dongsheng Cao, and 1 others. 2024b. Leveraging language model for advanced multiprop-erty molecular optimization via prompt engineering. Nature Machine Intelligence, pages 1–11. find
  121. Yingce Xia, Peiran Jin, Shufang Xie, Liang He, Chuan Cao, Renqian Luo, Guoqing Liu, Yue Wang, Zequn Liu, Yuan-Jyue Chen, and 1 others. 2025. Naturelm: Deciphering the language of nature for scientific discovery. arXiv preprint arXiv:2502.07527. — [arXiv:2502.07527](https://arxiv.org/abs/2502.07527) find
  122. Jiaxuan You, Bowen Liu, Zhitao Ying, Vijay Pande, and Jure Leskovec. 2018. Graph convolutional policy network for goal-directed molecular graph generation. Advances in neural information processing systems, 31. find
  123. Botao Yu, Frazier N Baker, Ziqi Chen, Xia Ning, and Huan Sun. 2024a. Llasmol: Advancing large language models for chemistry with a large-scale, comprehensive, high-quality instruction tuning dataset. arXiv preprint arXiv:2402.09391. find
  124. Ruiyao Xu and Kaize Ding. 2026. Gnn-as-judge: Unleashing the power of llms for graph learning with gnn feedback. arXiv preprint arXiv:2604.08553. — [arXiv:2604.08553](https://arxiv.org/abs/2604.08553) find
  125. Botao Yu, Frazier N. Baker, Ziqi Chen, Xia Ning, and Huan Sun. 2024b. Llasmol: Advancing large language models for chemistry with a large-scale, comprehensive, high-quality instruction tuning dataset. arXiv preprint arXiv:2402.09391. find
  126. Ruiyao Xu, Noelle I Samia, and Han Liu. 2026. Ds2-instruct: Domain-specific data synthesis for large language models instruction tuning. In Findings of the Association for Computational Linguistics: EACL 2026, pages 3368–3384.
  127. Jiajun Yu, Yizhen Zheng, Huan Yee Koh, Shirui Pan, Tianyue Wang, and Haishuai Wang. 2025. Collaborative expert llms guided multi-objective molecular optimization. arXiv preprint arXiv:2503.03503. — [arXiv:2503.03503](https://arxiv.org/abs/2503.03503) find
  128. Jingfeng Yang, Hongye Jin, Ruixiang Tang, Xiaotian Han, Qizhang Feng, Haoming Jiang, Bing Yin, and Xia Hu. 2023. Harnessing the power of llms in practice: A survey on chatgpt and beyond. arXiv preprint arXiv:2304.13712.
  129. Chengxi Zang and Fei Wang. 2020. Moflow: an invertible flow model for generating molecular graphs. In Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pages 617–626. find
  130. Nianzu Yang, Huaijin Wu, Kaipeng Zeng, Yang Li, Siyuan Bao, and Junchi Yan. 2024a. Molecule generation for drug design: a graph learning perspective. Fundamental Research. find
  131. Xiangxiang Zeng, Fei Wang, Yuan Luo, Seung-gu Kang, Jian Tang, Felice C Lightstone, Evandro F Fang, Wendy Cornell, Ruth Nussinov, and Feixiong Cheng. 2022. Deep generative molecular design reshapes drug discovery. Cell Reports Medicine, 3(12). find
  132. Nianzu Yang, Kaipeng Zeng, Qitian Wu, Xiaosong Jia, and Junchi Yan. 2022. Learning substructure invariance for out-of-distribution molecular representations. Advances in Neural Information Processing Systems, 35:12964–12978. find
  133. Di Zhang, Wei Liu, Qian Tan, Jingdan Chen, Hang Yan, Yuliang Yan, Jiatong Li, Weiran Huang, Xiangyu Yue, Wanli Ouyang, and 1 others. 2024a. Chemllm: A chemical large language model. arXiv preprint arXiv:2402.06852. find
  134. Zonglin Yang, Wanhao Liu, Ben Gao, Yujie Liu, Wei Li, Tong Xie, Lidong Bing, Wanli Ouyang, Erik Cambria, and Dongzhan Zhou. 2025. Moose-chem2: Exploring llm limits in fine-grained scientific hypothesis discovery via hierarchical search. arXiv preprint arXiv:2505.19209. — [arXiv:2505.19209](https://arxiv.org/abs/2505.19209) find
  135. Juzheng Zhang, Yatao Bian, Yongqiang Chen, and Quanming Yao. 2024b. Unimot: Unified molecule-text language model with discrete token representation. arXiv preprint arXiv:2408.00863. — [arXiv:2408.00863](https://arxiv.org/abs/2408.00863) find
  136. Zonglin Yang, Wanhao Liu, Ben Gao, Tong Xie, Yuqiang Li, Wanli Ouyang, Soujanya Poria, Erik Cambria, and Dongzhan Zhou. 2024b. Moose-chem: Large language models for rediscovering unseen chemistry scientific hypotheses. arXiv preprint arXiv:2410.07076. find
  137. Yang Yao, Xin Wang, Zeyang Zhang, Yijian Qin, Ziwei Zhang, Xu Chu, Yuekui Yang, Wenwu Zhu, and Hong Mei. 2024. Exploring the potential of large language models in graph generation. arXiv preprint arXiv:2403.14358. — [arXiv:2403.14358](https://arxiv.org/abs/2403.14358) find
  138. Geyan Ye, Xibao Cai, Houtim Lai, Xing Wang, Junhong Huang, Longyue Wang, Wei Liu, and Xiangxiang Zeng. 2025. Drugassist: A large language model for molecule optimization. Briefings in Bioinformatics, 26(1):bbae693. find
  139. Odin Zhang, Haitao Lin, Hui Zhang, Huifeng Zhao, Yufei Huang, Chang-Yu Hsieh, Peichen Pan, and Tingjun Hou. 2024c. Deep lead optimization: Leveraging generative ai for structural modification. Journal of the American Chemical Society, 146(46):31357–31370. find
  140. Peixuan Zhang, Chang Zhou, Ziyuan Zhang, Hualuo Liu, Chunjie Zhang, Jingqi Liu, Xiaohui Zhou, Xi Chen, Shuchen Weng, Si Li, and Boxin Shi. 2026. A benchmark and multi-agent system for instruction-driven cinematic video compilation. arXiv preprint arXiv:2604.10456. — [arXiv:2604.10456](https://arxiv.org/abs/2604.10456) find
  141. Qiang Zhang, Keyan Ding, Tianwen Lv, Xinda Wang, Qingyu Yin, Yiwen Zhang, Jing Yu, Yuhao Wang, Xiaotong Li, Zhuoyi Xiang, and 1 others. 2025. Scientific large language models: A survey on biological & chemical domains. ACM Computing Surveys, 57(6):1–38. find
  142. Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, and 1 others. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223.
  143. Alex Zhavoronkov, Yan A Ivanenkov, Alex Aliper, Mark S Veselov, Vladimir A Aladinskiy, Anastasiya V Aladinskaya, Victor A Terentiev, Daniil A Polykovskiy, Maksim D Kuznetsov, Arip Asadulaev, and 1 others. 2019. Deep learning enables rapid identification of potent ddr1 kinase inhibitors. Nature biote… find
  144. Yizhen Zheng, Huan Yee Koh, Maddie Yang, Li Li, Lauren T May, Geoffrey I Webb, Shirui Pan, and George Church. 2024. Large language models in drug discovery and development: From disease mechanisms to clinical trials. arXiv preprint arXiv:2409.04481. — [arXiv:2409.04481](https://arxiv.org/abs/2409.04481) find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/wang-2026-survey-large-language-models-text/