---
title: "Training a Scientific Reasoning Model for Chemistry (2025)"
description: "The authors release the weights, the benchmark and the reward functions. 116 references, cited by 5 papers here."
authors: ["Siddharth M. Narayanan", "James D. Braza", "Ryan-Rhys Griffiths", "Albert Bou", "Geemi Wellawatte", "Mayk Caldas Ramos", "Ludovico Mitchener", "Samuel G. Rodriques", "Andrew D. White"]
year: 2025
venue: "arXiv:2506.17238"
source: "https://arxiv.org/abs/2506.17238"
doi: "10.48550/arxiv.2506.17238"
arxiv: "2506.17238"
licence: "CC BY 4.0 (arXiv)"
licence_url: "http://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/narayanan-2025-training-scientific-reasoning-model/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/narayanan-2025-training-scientific-reasoning-model/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/8/) / Training a Scientific Reasoning Model for Chemistry

# Training a Scientific Reasoning Model for Chemistry

**Authors:** [Siddharth M. Narayanan](https://md.research.elamur.ai/free/en/authors/siddharth-narayanan/), [James D. Braza](https://md.research.elamur.ai/free/en/authors/james-d-braza/), [Ryan-Rhys Griffiths](https://md.research.elamur.ai/free/en/authors/ryan-rhys-griffiths/), [Albert Bou](https://md.research.elamur.ai/free/en/authors/albert-bou/), [Geemi Wellawatte](https://md.research.elamur.ai/free/en/authors/geemi-wellawatte/), [Mayk Caldas Ramos](https://md.research.elamur.ai/free/en/authors/mayk-caldas-ramos/), [Ludovico Mitchener](https://md.research.elamur.ai/free/en/authors/ludovico-mitchener/), [Samuel G. Rodriques](https://md.research.elamur.ai/free/en/authors/samuel-g-rodriques/) and [Andrew D. White](https://md.research.elamur.ai/free/en/authors/andrew-d-white/) · **Year:** 2025 · **Venue:** arXiv:2506.17238 · **Licence:** [CC BY 4.0 (arXiv)](http://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2506.17238) · [PDF](https://arxiv.org/pdf/2506.17238) · [DOI 10.48550/arxiv.2506.17238](https://doi.org/10.48550/arxiv.2506.17238) · [arXiv 2506.17238](https://arxiv.org/abs/2506.17238) · [OpenAlex](https://openalex.org/W6948247378)

**Citations:** 10 citations (OpenAlex, 2026-10-14) · [5](https://md.research.elamur.ai/free/en/papers/narayanan-2025-training-scientific-reasoning-model/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper asks whether reasoning-style post-training, which has mostly been shown to work in maths and coding, also transfers to chemistry. The FutureHouse team built ether0, a 24B model derived from Mistral-Small-24B. It thinks in natural language and gives its final answers as SMILES strings. No extra chemistry pretraining was done. The training data consists of about 640k problems drawn from real experimental data (sources such as ChEMBL, COCONUT, ORD and PubChem), and every answer can be checked automatically by code, RDKit, or trained predictors. Training proceeds in stages:

* supervised fine-tuning on distilled reasoning traces,
* GRPO-trained task specialists,
* rejection sampling and distillation into a generalist,
* final GRPO across all tasks, using a dynamic curriculum.

ether0 beats frontier LLMs, human experts and general chemistry models on molecular design, especially on open-answer tasks, while needing less data than specialised models. This matters because it suggests that verifiable-reward RL could yield data-efficient reasoning models in other sciences too. The authors release the weights, the benchmark and the reward functions.

## Key points
- The dataset contains 640,730 problems in 18 task families split into 375 subtasks. Examples include solubility editing, retrosynthesis (reactants checked against a Bloom filter of purchasable compounds, products checked with Molecular Transformer), IUPAC-to-SMILES conversion, and multiple-choice questions on scent, BBB permeability and receptor binding.
- In zero-shot evaluation ether0 scores 50.1% on the test set, close to o1-2024-12-17 at 52.2%. With one-shot prompting it surpasses every frontier model evaluated.
- An ablation trains a model on the same distillation data with the reasoning removed. The reasoning model wins on most tasks, with clear gains on molecular formula and functional group, but little benefit on solubility editing or SMILES completion.
- Over the course of training, behaviours such as verification, backtracking, subgoal setting and backward chaining become more frequent selectively, in tasks where structured reasoning helps.
- Limitations:
  - weak coverage of inorganic chemistry and crystal structures;
  - degraded general chat and multi-turn instruction-following;
  - no tool calling.

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

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 19,503 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,621 works · [🧮 Computational Theory and Mathematics](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) · 496 works · [🧱 Materials Science](https://md.research.elamur.ai/free/en/shelves/materials-science/) · 58 works · [🧱 Materials Chemistry](https://md.research.elamur.ai/free/en/shelves/materials-science/materials-chemistry/) · 58 works

🧭 Topics (1): [🧮 Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/) · 1,948 works

## Cite

Cite as: Siddharth M. Narayanan, James D. Braza, Ryan-Rhys Griffiths, Albert Bou, Geemi Wellawatte, Mayk Caldas Ramos, Ludovico Mitchener, Samuel G. Rodriques and Andrew D. White. 2025. Training a Scientific Reasoning Model for Chemistry. arXiv:2506.17238.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{narayanan2025training,
  title = {{Training a Scientific Reasoning Model for Chemistry}},
  author = {Siddharth M. Narayanan, James D. Braza, Ryan-Rhys Griffiths, Albert Bou, Geemi Wellawatte, Mayk Caldas Ramos, Ludovico Mitchener, Samuel G. Rodriques and Andrew D. White},
  year = {2025},
  doi = {10.48550/arxiv.2506.17238},
  eprint = {2506.17238},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2506.17238}
}
```

- [← previous ToolHop: A Query-Driven Benchmark for Evaluating Large Language Models in Multi-Hop Tool Use](https://md.research.elamur.ai/free/en/papers/ye-2025-toolhop-query-driven-benchmark-evaluating/)
- [next → Understanding Figurative Meaning through Explainable Visual Entailment](https://md.research.elamur.ai/free/en/papers/saakyan-2025-understanding-figurative-meaning-through-explainable/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/8/)

## References

116 references, 37 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019. [find](https://scholar.google.com/scholar?q=Alec+Radford%2C+Jeffrey+Wu%2C+Rewon+Child%2C+David+Luan%2C+Dario+Amodei%2C+Ilya+Sutskever%2C+et+al%2E+Language+models+are+unsupervised+multitask+learners%2E+OpenAI+blog%2C+1%288%29%3A9%2C+2019%2E)
2. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. [Language models are few-shot learners](https://md.research.elamur.ai/free/en/papers/brown-2020-language-models-few-shot-learners/). Advances in Neural Information Processing Systems, 33:1877– 1901, 2020.
3. Jared Kaplan, Sam McCandlish, Tom Henighan, Tom B Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei. [Scaling laws for neural language models](https://md.research.elamur.ai/free/en/papers/kaplan-2020-scaling-laws-neural-language-models/). arXiv preprint arXiv:2001.08361, 2020.
4. Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena Buchatskaya, Trevor Cai, Eliza Rutherford, Diego de Las Casas, Lisa Anne Hendricks, Johannes Welbl, Aidan Clark, et al. [Training compute-optimal large language models](https://md.research.elamur.ai/free/en/papers/hoffmann-2022-training-compute-optimal-large-language/). In Proceedings of the 36th International Conference on Neural Information…
5. Bradley Brown, Jordan Juravsky, Ryan Ehrlich, Ronald Clark, Quoc V Le, Christopher Ré, and Azalia Mirhoseini. [Large language monkeys: Scaling inference compute with repeated sampling](https://md.research.elamur.ai/free/en/papers/brown-2024-large-language-monkeys-scaling-inference/). arXiv preprint arXiv:2407.21787, 2024.
6. Siddharth Narayanan, James D Braza, Ryan-Rhys Griffiths, Manu Ponnapati, Albert Bou, Jon Laurent, Ori Kabeli, Geemi Wellawatte, Sam Cox, Samuel G Rodriques, et al. [Aviary: training language agents on challenging scientific tasks](https://md.research.elamur.ai/free/en/papers/narayanan-2024-aviary-training-language-agents/). arXiv preprint arXiv:2412.21154, 2024.
7. Niklas Muennighoff, Zitong Yang, Weijia Shi, Xiang Lisa Li, Li Fei-Fei, Hannaneh Hajishirzi, Luke Zettlemoyer, Percy Liang, Emmanuel Candès, and Tatsunori Hashimoto. [s1: Simple test-time scaling](https://md.research.elamur.ai/free/en/papers/muennighoff-2025-s1-simple-test-time-scaling/). arXiv preprint arXiv:2501.19393, 2025.
8. Ekin Akyürek, Mehul Damani, Adam Zweiger, Linlu Qiu, Han Guo, Jyothish Pari, Yoon Kim, and Jacob Andreas. [The surprising effectiveness of test-time training for few-shot learning](https://md.research.elamur.ai/free/en/papers/akyurek-2024-surprising-effectiveness-test-time-training/). arXiv preprint arXiv:2411.07279, 2024.
9. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). Advances in Neural Information Processing Systems, 35:24824–24837, 2022.
10. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). Advances in Neural Information Processing Systems, 35:22199–22213, 2022.
11. Anthropic. Claude 3.7 Sonnet and Claude code, February 2025. Accessed: 2025-04-26. [find](https://scholar.google.com/scholar?q=Anthropic%2E+Claude+3%2E7+Sonnet+and+Claude+code%2C+February+2025%2E+Accessed%3A+2025%2D04%2D26%2E)
12. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al. [OpenAI o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). arXiv preprint arXiv:2412.16720, 2024.
13. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. [DeepSeek-R1: Incentivizing reasoning capability in LLMs via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). arXiv preprint arXiv:2501.12948, 2025.
14. Kimi Team, Angang Du, Bofei Gao, Bowei Xing, Changjiu Jiang, Cheng Chen, Cheng Li, Chenjun Xiao, Chenzhuang Du, Chonghua Liao, et al. [Kimi k1.5: Scaling reinforcement learning with LLMs](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k1-5-scaling-reinforcement/). arXiv preprint arXiv:2501.12599, 2025.
15. Michael Luo, Sijun Tan, Justin Wong, Xiaoxiang Shi, William Y. Tang, Manan Roongta, Colin Cai, Jeffrey Luo, Li Erran Li, Raluca Ada Popa, and Ion Stoica. DeepScaleR: Surpassing o1-preview with a 1.5B model by scaling RL. [https://pretty-radio-b75.notion.si](https://pretty-radio-b75.notion.si) te/DeepScaleR-Surpassing-O1-Preview-with-a-1… [↗](https://pretty-radio-b75.notion.si)
16. Michael Luo, Sijun Tan, Roy Huang, Xiaoxiang Shi, Rachel Xin, Colin Cai, Ameen Patel, Alpay Ariyak, Qingyang Wu, Ce Zhang, Li Erran Li, Raluca Ada Popa, and Ion Stoica. Deepcoder: A fully open-source 14B coder at O3-mini level. https://pretty-radio-b75 .notion.site/DeepCoder-A-Fully-Open-Source-14B-… [find](https://scholar.google.com/scholar?q=Michael+Luo%2C+Sijun+Tan%2C+Roy+Huang%2C+Xiaoxiang+Shi%2C+Rachel+Xin%2C+Colin+Cai%2C+Ameen+Patel%2C+Alpay+Ariyak%2C+Qingyang+Wu%2C+Ce+Zhang%2C+Li+Erran+Li%2C+Raluca+Ada+Popa%2C+and+Ion+Stoica%2E+Deepcoder%3A+A+fully+open%2Dsource+)
17. Akhiad Bercovich, Itay Levy, Izik Golan, Mohammad Dabbah, Ran El-Yaniv, Omri Puny, Ido Galil, Zach Moshe, Tomer Ronen, Najeeb Nabwani, et al. [Llama-Nemotron: Efficient reasoning models](https://md.research.elamur.ai/free/en/papers/bercovich-2025-llama-nemotron-efficient-reasoning-models/). arXiv preprint arXiv:2505.00949, 2025.
18. Syeda Nahida Akter, Shrimai Prabhumoye, Matvei Novikov, Seungju Han, Ying Lin, Evelina Bakhturi, Eric Nyberg, Yejin Choi, Mostofa Patwary, Mohammad Shoeybi, et al. [Nemotron-CrossThink: Scaling self-learning beyond math reasoning](https://md.research.elamur.ai/free/en/papers/akter-2026-nemotron-crossthink-scaling-self-learning/). arXiv preprint arXiv:2504.13941, 2025.
19. Aaron Blakeman, Aarti Basant, Abhinav Khattar, Adithya Renduchintala, Akhiad Bercovich, Aleksander Ficek, Alexis Bjorlin, Ali Taghibakhshi, Amala Sanjay Deshmukh, Ameya Sunil Mahabaleshwarkar, et al. [Nemotron-H: A family of accurate and efficient hybrid Mamba-transformer models](https://md.research.elamur.ai/free/en/papers/blakeman-2025-nemotron-h-family-accurate-efficient/). arXiv preprint arXiv…
20. Simon Arridge, Peter Maass, Ozan Öktem, and Carola-Bibiane Schönlieb. Solving inverse problems using data-driven models. Acta Numerica, 28:1–174, 2019. [find](https://scholar.google.com/scholar?q=Simon+Arridge%2C+Peter+Maass%2C+Ozan+%C3%96ktem%2C+and+Carola%2DBibiane+Sch%C3%B6nlieb%2E+Solving+inverse+problems+using+data%2Ddriven+models%2E+Acta+Numerica%2C+28%3A1%E2%80%93174%2C+2019%2E)
21. Gregory Ongie, Ajil Jalal, Christopher A Metzler, Richard G Baraniuk, Alexandros G Dimakis, and Rebecca Willett. Deep learning techniques for inverse problems in imaging. IEEE Journal on Selected Areas in Information Theory, 1(1):39–56, 2020. [find](https://scholar.google.com/scholar?q=Gregory+Ongie%2C+Ajil+Jalal%2C+Christopher+A+Metzler%2C+Richard+G+Baraniuk%2C+Alexandros+G+Dimakis%2C+and+Rebecca+Willett%2E+Deep+learning+techniques+for+inverse+problems+in+imaging%2E+IEEE+Journal+on+Selected+Area)
22. Ali Siahkoohi, Gabrio Rizzuti, Rafael Orozco, and Felix J Herrmann. Reliable amortized variational inference with physics-based latent distribution correction. Geophysics, 88(3):R297– R322, 2023. [find](https://scholar.google.com/scholar?q=Ali+Siahkoohi%2C+Gabrio+Rizzuti%2C+Rafael+Orozco%2C+and+Felix+J+Herrmann%2E+Reliable+amortized+variational+inference+with+physics%2Dbased+latent+distribution+correction%2E+Geophysics%2C+88%283%29%3AR297%E2%80%93+R322%2C+2023%2E)
23. Hongkai Zheng, Wenda Chu, Bingliang Zhang, Zihui Wu, Austin Wang, Berthy T Feng, Caifeng Zou, Yu Sun, Nikola Kovachki, Zachary E Ross, et al. InverseBench: Benchmarking plug-and-play diffusion priors for inverse problems in physical sciences. arXiv preprint arXiv:2503.11043, 2025. — [arXiv:2503.11043](https://arxiv.org/abs/2503.11043) [find](https://scholar.google.com/scholar?q=Hongkai+Zheng%2C+Wenda+Chu%2C+Bingliang+Zhang%2C+Zihui+Wu%2C+Austin+Wang%2C+Berthy+T+Feng%2C+Caifeng+Zou%2C+Yu+Sun%2C+Nikola+Kovachki%2C+Zachary+E+Ross%2C+et+al%2E+InverseBench%3A+Benchmarking+plug%2Dand%2Dplay+diffusion+priors+)
24. Daniel Lesnic. Inverse problems with applications in science and engineering. Chapman and Hall/CRC, 2021. [find](https://scholar.google.com/scholar?q=Daniel+Lesnic%2E+Inverse+problems+with+applications+in+science+and+engineering%2E+Chapman+and+Hall%2FCRC%2C+2021%2E)
25. Kanishk Gandhi, Ayush Chakravarthy, Anikait Singh, Nathan Lile, and Noah D Goodman. [Cognitive behaviors that enable self-improving reasoners, or, four habits of highly effective stars](https://md.research.elamur.ai/free/en/papers/gandhi-2025-cognitive-behaviors-that-enable-self/). arXiv preprint arXiv:2503.01307, 2025.
26. Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. [Measuring massive multitask language understanding](https://md.research.elamur.ai/free/en/papers/hendrycks-2020-measuring-massive-multitask-language-understanding/). In International Conference on Learning Representations, 2021.
27. Yubo Wang, Xueguang Ma, Ge Zhang, Yuansheng Ni, Abhranil Chandra, Shiguang Guo, Weiming Ren, Aaran Arulraj, Xuan He, Ziyan Jiang, et al. [MMLU-Pro: A more robust and challenging multi-task language understanding benchmark](https://md.research.elamur.ai/free/en/papers/wang-2024-mmlu-pro-more-robust-challenging/). In The Thirty-Eighth Conference on Neural Information Processing Systems Datas…
28. David Rein, Betty Li Hou, Asa Cooper Stickland, Jackson Petty, Richard Yuanzhe Pang, Julien Dirani, Julian Michael, and Samuel R. Bowman. [GPQA: A graduate-level Google-Proof Q&A benchmark](https://md.research.elamur.ai/free/en/papers/rein-2023-gpqa-graduate-level-google-proof/). In First Conference on Language Modeling, 2024.
29. David Weininger. 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, 1988. [find](https://scholar.google.com/scholar?q=David+Weininger%2E+SMILES%2C+a+chemical+language+and+information+system%2E+1%2E+introduction+to+methodology+and+encoding+rules%2E+Journal+of+Chemical+Information+and+Computer+Sciences%2C+28%281%29%3A31%E2%80%9336%2C+1988%2E)
30. David Weininger, Arthur Weininger, and Joseph L Weininger. SMILES. 2. algorithm for generation of unique SMILES notation. Journal of Chemical Information and Computer Sciences, 29(2):97–101, 1989. [find](https://scholar.google.com/scholar?q=David+Weininger%2C+Arthur+Weininger%2C+and+Joseph+L+Weininger%2E+SMILES%2E+2%2E+algorithm+for+generation+of+unique+SMILES+notation%2E+Journal+of+Chemical+Information+and+Computer+Sciences%2C+29%282%29%3A97%E2%80%93101%2C+1989%2E)
31. David Weininger. SMILES. 3. DEPICT. graphical depiction of chemical structures. Journal of Chemical Information and Computer Sciences, 30(3):237–243, 1990. [find](https://scholar.google.com/scholar?q=David+Weininger%2E+SMILES%2E+3%2E+DEPICT%2E+graphical+depiction+of+chemical+structures%2E+Journal+of+Chemical+Information+and+Computer+Sciences%2C+30%283%29%3A237%E2%80%93243%2C+1990%2E)
32. Daniel Kahneman. Thinking, fast and slow. Farrar, Straus and Giroux, New York, 2011. [find](https://scholar.google.com/scholar?q=Daniel+Kahneman%2E+Thinking%2C+fast+and+slow%2E+Farrar%2C+Straus+and+Giroux%2C+New+York%2C+2011%2E)
33. Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information processing systems, 36:11809–11822, 2023. [find](https://scholar.google.com/scholar?q=Shunyu+Yao%2C+Dian+Yu%2C+Jeffrey+Zhao%2C+Izhak+Shafran%2C+Tom+Griffiths%2C+Yuan+Cao%2C+and+Karthik+Narasimhan%2E+Tree+of+thoughts%3A+Deliberate+problem+solving+with+large+language+models%2E+Advances+in+Neural+Informati)
34. Shibo Hao, Yi Gu, Haodi Ma, Joshua Hong, Zhen Wang, Daisy Wang, and Zhiting Hu. Reasoning with language model is planning with world model. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8154–8173, 2023. [find](https://scholar.google.com/scholar?q=Shibo+Hao%2C+Yi+Gu%2C+Haodi+Ma%2C+Joshua+Hong%2C+Zhen+Wang%2C+Daisy+Wang%2C+and+Zhiting+Hu%2E+Reasoning+with+language+model+is+planning+with+world+model%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+i)
35. Zitian Gao, Boye Niu, Xuzheng He, Haotian Xu, Hongzhang Liu, Aiwei Liu, Xuming Hu, and Lijie Wen. Interpretable contrastive Monte Carlo tree search reasoning. arXiv preprint arXiv:2410.01707, 2024. — [arXiv:2410.01707](https://arxiv.org/abs/2410.01707) [find](https://scholar.google.com/scholar?q=Zitian+Gao%2C+Boye+Niu%2C+Xuzheng+He%2C+Haotian+Xu%2C+Hongzhang+Liu%2C+Aiwei+Liu%2C+Xuming+Hu%2C+and+Lijie+Wen%2E+Interpretable+contrastive+Monte+Carlo+tree+search+reasoning%2E+arXiv+preprint+arXiv%3A2410%2E01707%2C+2024%2E+%E2%80%94+)
36. Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. Let’s verify step by step. In The Twelfth International Conference on Learning Representations, 2024. — [Let's Verify Step by Step](https://md.research.elamur.ai/free/en/papers/lightman-2023-let-s-verify-step-step/)
37. OpenAI. OpenAI o3 and o4-mini system card, April 2025. Accessed: 2025-05-08. [find](https://scholar.google.com/scholar?q=OpenAI%2E+OpenAI+o3+and+o4%2Dmini+system+card%2C+April+2025%2E+Accessed%3A+2025%2D05%2D08%2E)
38. Yiwei Qin, Xuefeng Li, Haoyang Zou, Yixiu Liu, Shijie Xia, Zhen Huang, Yixin Ye, Weizhe Yuan, Hector Liu, Yuanzhi Li, et al. O1 replication journey: A strategic progress report–part 1. arXiv preprint arXiv:2410.[18982, 2024](https://md.research.elamur.ai/free/en/papers/qin-2024-o1-replication-journey-strategic-progress/).
39. Zhen Huang, Haoyang Zou, Xuefeng Li, Yixiu Liu, Yuxiang Zheng, Ethan Chern, Shijie Xia, Yiwei Qin, Weizhe Yuan, and Pengfei Liu. O1 replication journey–part 2: Surpassing O1-preview through simple distillation, big progress or bitter lesson? arXiv preprint arXiv:2411.[16489, 2024](https://md.research.elamur.ai/free/en/papers/huang-2024-o1-replication-journey-part-2/).
40. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, YK Li, and Daya Guo. [DeepSeekMath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300, 2024.
41. Zhongzhen Huang, Gui Geng, Shengyi Hua, Zhen Huang, Haoyang Zou, Shaoting Zhang, Pengfei Liu, and Xiaofan Zhang. O1 replication journey–part 3: Inference-time scaling for medical reasoning. arXiv preprint arXiv:2501.06458, 2025. — [arXiv:2501.06458](https://arxiv.org/abs/2501.06458) [find](https://scholar.google.com/scholar?q=Zhongzhen+Huang%2C+Gui+Geng%2C+Shengyi+Hua%2C+Zhen+Huang%2C+Haoyang+Zou%2C+Shaoting+Zhang%2C+Pengfei+Liu%2C+and+Xiaofan+Zhang%2E+O1+replication+journey%E2%80%93part+3%3A+Inference%2Dtime+scaling+for+medical+reasoning%2E+arXiv+prep)
42. Zhen Huang, Zengzhi Wang, Shijie Xia, Xuefeng Li, Haoyang Zou, Ruijie Xu, Run-Ze Fan, Lyumanshan Ye, Ethan Chern, Yixin Ye, et al. [OlympicArena: Benchmarking multi-discipline cognitive reasoning for superintelligent AI](https://md.research.elamur.ai/free/en/papers/huang-2024-olympicarena-benchmarking-multi-discipline-cognitive/). Advances in Neural Information Processing Systems, 37:19209–19253, 2024.
43. Long Phan, Alice Gatti, Ziwen Han, Nathaniel Li, Josephina Hu, Hugh Zhang, Chen Bo Calvin Zhang, Mohamed Shaaban, John Ling, Sean Shi, et al. Humanity’s last exam. arXiv preprint arXiv:2501.[14249, 2025](https://md.research.elamur.ai/free/en/papers/phan-2025-humanity-s-last-exam/).
44. Taicheng Guo, Kehan Guo, Bozhao Nan, Zhenwen Liang, Zhichun Guo, Nitesh V Chawla, Olaf Wiest, and Xiangliang Zhang. What can large language models do in chemistry? a comprehensive benchmark on eight tasks. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks… [find](https://scholar.google.com/scholar?q=Taicheng+Guo%2C+Kehan+Guo%2C+Bozhao+Nan%2C+Zhenwen+Liang%2C+Zhichun+Guo%2C+Nitesh+V+Chawla%2C+Olaf+Wiest%2C+and+Xiangliang+Zhang%2E+What+can+large+language+models+do+in+chemistry%3F+a+comprehensive+benchmark+on+eight+t)
45. Tianhao Li, Jingyu Lu, Chuangxin Chu, Tianyu Zeng, Yujia Zheng, Mei Li, Haotian Huang, Bin Wu, Zuoxian Liu, Kai Ma, et al. SciSafeEval: a comprehensive benchmark for safety alignment of large language models in scientific tasks. arXiv preprint arXiv:2410.03769, 2024. — [arXiv:2410.03769](https://arxiv.org/abs/2410.03769) [find](https://scholar.google.com/scholar?q=Tianhao+Li%2C+Jingyu+Lu%2C+Chuangxin+Chu%2C+Tianyu+Zeng%2C+Yujia+Zheng%2C+Mei+Li%2C+Haotian+Huang%2C+Bin+Wu%2C+Zuoxian+Liu%2C+Kai+Ma%2C+et+al%2E+SciSafeEval%3A+a+comprehensive+benchmark+for+safety+alignment+of+large+language)
46. Kehua Feng, Keyan Ding, Weijie Wang, Xiang Zhuang, Zeyuan Wang, Ming Qin, Yu Zhao, Jianhua Yao, Qiang Zhang, and Huajun Chen. [SciKnowEval: Evaluating multi-level scientific knowledge of large language models](https://md.research.elamur.ai/free/en/papers/feng-2024-sciknoweval-evaluating-multi-level-scientific/). arXiv preprint arXiv:2406.09098, 2024.
47. Daniil A Boiko, Robert MacKnight, Ben Kline, and Gabe Gomes. [Autonomous chemical research with large language models](https://md.research.elamur.ai/free/en/papers/boiko-2023-autonomous-chemical-research-large-language/). Nature, 624(7992):570–578, 2023.
48. Andres M. Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D White, and Philippe Schwaller. Augmenting large language models with chemistry tools. Nature Machine Intelligence, 6(5):525–535, 2024. [find](https://scholar.google.com/scholar?q=Andres+M%2E+Bran%2C+Sam+Cox%2C+Oliver+Schilter%2C+Carlo+Baldassari%2C+Andrew+D+White%2C+and+Philippe+Schwaller%2E+Augmenting+large+language+models+with+chemistry+tools%2E+Nature+Machine+Intelligence%2C+6%285%29%3A525%E2%80%93535%2C+20)
49. Andres M Bran, Theo A Neukomm, Daniel P Armstrong, Zlatko Jončev, and Philippe Schwaller. Chemical reasoning in LLMs unlocks steerable synthesis planning and reaction mechanism elucidation. arXiv preprint arXiv:2503.08537, 2025. [find](https://scholar.google.com/scholar?q=Andres+M+Bran%2C+Theo+A+Neukomm%2C+Daniel+P+Armstrong%2C+Zlatko+Jonc%CC%8Cev%2C+and+Philippe+Schwaller%2E+Chemical+reasoning+in+LLMs+unlocks+steerable+synthesis+planning+and+reaction+mechanism+elucidation%2E+arXiv+pre)
50. Sirui Ouyang, Zhuosheng Zhang, Bing Yan, Xuan Liu, Yejin Choi, Jiawei Han, and Lianhui Qin. Structured chemistry reasoning with large language models. In Proceedings of the 41st International Conference on Machine Learning, pages 38937–38952, 2024. [find](https://scholar.google.com/scholar?q=Sirui+Ouyang%2C+Zhuosheng+Zhang%2C+Bing+Yan%2C+Xuan+Liu%2C+Yejin+Choi%2C+Jiawei+Han%2C+and+Lianhui+Qin%2E+Structured+chemistry+reasoning+with+large+language+models%2E+In+Proceedings+of+the+41st+International+Conferen)
51. Yunhui Jang, Jaehyung Kim, and Sungsoo Ahn. Chain-of-thoughts for molecular understanding. arXiv preprint arXiv:2410.05610, 2024. — [arXiv:2410.05610](https://arxiv.org/abs/2410.05610) [find](https://scholar.google.com/scholar?q=Yunhui+Jang%2C+Jaehyung+Kim%2C+and+Sungsoo+Ahn%2E+Chain%2Dof%2Dthoughts+for+molecular+understanding%2E+arXiv+preprint+arXiv%3A2410%2E05610%2C+2024%2E+%E2%80%94+%5BarXiv%3A2410%2E05610%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2410%2E05610%29)
52. Vignesh Prabhakar, Md Amirul Islam, Adam Atanas, Yao-Ting Wang, Joah Han, Aastha Jhunjhunwala, Rucha Apte, Robert Clark, Kang Xu, Zihan Wang, et al. [Omniscience: A domain-specialized llm for scientific reasoning and discovery](https://md.research.elamur.ai/free/en/papers/prabhakar-2025-omniscience-domain-specialized-llm-scientific/). arXiv preprint arXiv:2503.17604, 2025.
53. Yuxiang Lai, Jike Zhong, Ming Li, Shitian Zhao, and Xiaofeng Yang. Med-R1: Reinforcement learning for generalizable medical reasoning in vision-language models. arXiv preprint arXiv:2503.13939, 2025. — [arXiv:2503.13939](https://arxiv.org/abs/2503.13939) [find](https://scholar.google.com/scholar?q=Yuxiang+Lai%2C+Jike+Zhong%2C+Ming+Li%2C+Shitian+Zhao%2C+and+Xiaofeng+Yang%2E+Med%2DR1%3A+Reinforcement+learning+for+generalizable+medical+reasoning+in+vision%2Dlanguage+models%2E+arXiv+preprint+arXiv%3A2503%2E13939%2C+2025%2E+)
54. Adibvafa Fallahpour, Andrew Magnuson, Purav Gupta, Shihao Ma, Jack Naimer, Arnav Shah, Haonan Duan, Omar Ibrahim, Hani Goodarzi, Chris J Maddison, et al. BioReason: Incentivizing multimodal biological reasoning within a DNA-LLM model. arXiv preprint arXiv:2505.23579, 2025. — [arXiv:2505.23579](https://arxiv.org/abs/2505.23579) [find](https://scholar.google.com/scholar?q=Adibvafa+Fallahpour%2C+Andrew+Magnuson%2C+Purav+Gupta%2C+Shihao+Ma%2C+Jack+Naimer%2C+Arnav+Shah%2C+Haonan+Duan%2C+Omar+Ibrahim%2C+Hani+Goodarzi%2C+Chris+J+Maddison%2C+et+al%2E+BioReason%3A+Incentivizing+multimodal+biological)
55. Nikolay Kochev, Svetlana Avramova, and Nina Jeliazkova. Ambit-SMIRKS: a software module for reaction representation, reaction search and structure transformation. Journal of Cheminformatics, 10(1):42, August 2018. [find](https://scholar.google.com/scholar?q=Nikolay+Kochev%2C+Svetlana+Avramova%2C+and+Nina+Jeliazkova%2E+Ambit%2DSMIRKS%3A+a+software+module+for+reaction+representation%2C+reaction+search+and+structure+transformation%2E+Journal+of+Cheminformatics%2C+10%281%29%3A42%2C)
56. Mayk Caldas Ramos and Andrew D White. Predicting small molecules solubility on endpoint devices using deep ensemble neural networks. Digital Discovery, 3(4):786, 2024. [find](https://scholar.google.com/scholar?q=Mayk+Caldas+Ramos+and+Andrew+D+White%2E+Predicting+small+molecules+solubility+on+endpoint+devices+using+deep+ensemble+neural+networks%2E+Digital+Discovery%2C+3%284%29%3A786%2C+2024%2E)
57. Barbara Zdrazil, Eloy Felix, Fiona Hunter, Emma J Manners, James Blackshaw, Sybilla Corbett, Marleen de Veij, Harris Ioannidis, David Mendez Lopez, Juan F Mosquera, et al. The ChEMBL database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods. Nucleic Acids… [find](https://scholar.google.com/scholar?q=Barbara+Zdrazil%2C+Eloy+Felix%2C+Fiona+Hunter%2C+Emma+J+Manners%2C+James+Blackshaw%2C+Sybilla+Corbett%2C+Marleen+de+Veij%2C+Harris+Ioannidis%2C+David+Mendez+Lopez%2C+Juan+F+Mosquera%2C+et+al%2E+The+ChEMBL+database+in+2023%3A)
58. Maria Sorokina, Peter Merseburger, Kohulan Rajan, Mehmet Aziz Yirik, and Christoph Steinbeck. COCONUT online: collection of open natural products database. Journal of Cheminformatics, 13(1):2, 2021. [find](https://scholar.google.com/scholar?q=Maria+Sorokina%2C+Peter+Merseburger%2C+Kohulan+Rajan%2C+Mehmet+Aziz+Yirik%2C+and+Christoph+Steinbeck%2E+COCONUT+online%3A+collection+of+open+natural+products+database%2E+Journal+of+Cheminformatics%2C+13%281%29%3A2%2C+2021%2E)
59. Venkata Chandrasekhar, Kohulan Rajan, Sri Ram Sagar Kanakam, Nisha Sharma, Viktor Weißenborn, Jonas Schaub, and Christoph Steinbeck. COCONUT 2.0: a comprehensive overhaul and curation of the collection of open natural products database. Nucleic Acids Research, 53(D1):D634–D643, 2025. [find](https://scholar.google.com/scholar?q=Venkata+Chandrasekhar%2C+Kohulan+Rajan%2C+Sri+Ram+Sagar+Kanakam%2C+Nisha+Sharma%2C+Viktor+Wei%C3%9Fenborn%2C+Jonas+Schaub%2C+and+Christoph+Steinbeck%2E+COCONUT+2%2E0%3A+a+comprehensive+overhaul+and+curation+of+the+collectio)
60. Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A Hunter, Costas Bekas, and Alpha A Lee. Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Central Science, 5(9):1572–1583, 2019. [find](https://scholar.google.com/scholar?q=Philippe+Schwaller%2C+Teodoro+Laino%2C+Th%C3%A9ophile+Gaudin%2C+Peter+Bolgar%2C+Christopher+A+Hunter%2C+Costas+Bekas%2C+and+Alpha+A+Lee%2E+Molecular+transformer%3A+a+model+for+uncertainty%2Dcalibrated+chemical+reaction+pred)
61. Jorge Medina and Andrew D White. Bloom filters for molecules. Journal of Cheminformatics, 15(1):95, 2023. [find](https://scholar.google.com/scholar?q=Jorge+Medina+and+Andrew+D+White%2E+Bloom+filters+for+molecules%2E+Journal+of+Cheminformatics%2C+15%281%29%3A95%2C+2023%2E)
62. Steven M Kearnes, Michael R Maser, Michael Wleklinski, Anton Kast, Abigail G Doyle, Spencer D Dreher, Joel M Hawkins, Klavs F Jensen, and Connor W Coley. The open reaction database. Journal of the American Chemical Society, 143(45):18820–18826, 2021. [find](https://scholar.google.com/scholar?q=Steven+M+Kearnes%2C+Michael+R+Maser%2C+Michael+Wleklinski%2C+Anton+Kast%2C+Abigail+G+Doyle%2C+Spencer+D+Dreher%2C+Joel+M+Hawkins%2C+Klavs+F+Jensen%2C+and+Connor+W+Coley%2E+The+open+reaction+database%2E+Journal+of+the+Ame)
63. Rocío Mercado, Steven M Kearnes, and Connor W Coley. Data sharing in chemistry: lessons learned and a case for mandating structured reaction data. Journal of Chemical Information and Modeling, 63(14):4253–4265, 2023. [find](https://scholar.google.com/scholar?q=Roc%C3%ADo+Mercado%2C+Steven+M+Kearnes%2C+and+Connor+W+Coley%2E+Data+sharing+in+chemistry%3A+lessons+learned+and+a+case+for+mandating+structured+reaction+data%2E+Journal+of+Chemical+Information+and+Modeling%2C+63%2814%29%3A)
64. Botao Yu, Frazier N. Baker, Ziqi Chen, Xia Ning, and Huan Sun. [LlaSMol: Advancing large language models for chemistry with a large-scale, comprehensive, high-quality instruction tuning dataset](https://md.research.elamur.ai/free/en/papers/yu-2024-llasmol-advancing-large-language-models/). In First Conference on Language Modeling, 2024.
65. Sunghwan Kim, Jie Chen, Tiejun Cheng, Asta Gindulyte, Jia He, Siqian He, Qingliang Li, Benjamin A Shoemaker, Paul A Thiessen, Bo Yu, et al. PubChem 2023 update. Nucleic Acids Research, 51(D1):D1373–D1380, 2023. [find](https://scholar.google.com/scholar?q=Sunghwan+Kim%2C+Jie+Chen%2C+Tiejun+Cheng%2C+Asta+Gindulyte%2C+Jia+He%2C+Siqian+He%2C+Qingliang+Li%2C+Benjamin+A+Shoemaker%2C+Paul+A+Thiessen%2C+Bo+Yu%2C+et+al%2E+PubChem+2023+update%2E+Nucleic+Acids+Research%2C+51%28D1%29%3AD1373%E2%80%93D1)
66. Andreas Keller, Margaret Hempstead, Iran A Gomez, Avery N Gilbert, and Leslie B Vosshall. An olfactory demography of a diverse metropolitan population. BMC Neuroscience, 13(1), October 2012. [find](https://scholar.google.com/scholar?q=Andreas+Keller%2C+Margaret+Hempstead%2C+Iran+A+Gomez%2C+Avery+N+Gilbert%2C+and+Leslie+B+Vosshall%2E+An+olfactory+demography+of+a+diverse+metropolitan+population%2E+BMC+Neuroscience%2C+13%281%29%2C+October+2012%2E)
67. C. Bushdid, M. O. Magnasco, L. B. Vosshall, and A. Keller. Humans can discriminate more than 1 trillion olfactory stimuli. Science, 343(6177):1370–1372, March 2014. [find](https://scholar.google.com/scholar?q=C%2E+Bushdid%2C+M%2E+O%2E+Magnasco%2C+L%2E+B%2E+Vosshall%2C+and+A%2E+Keller%2E+Humans+can+discriminate+more+than+1+trillion+olfactory+stimuli%2E+Science%2C+343%286177%29%3A1370%E2%80%931372%2C+March+2014%2E)
68. Neelansh Garg, Apuroop Sethupathy, Rudraksh Tuwani, Rakhi NK, Shubham Dokania, Arvind Iyer, Ayushi Gupta, Shubhra Agrawal, Navjot Singh, Shubham Shukla, Kriti Kathuria, Rahul Badhwar, Rakesh Kanji, Anupam Jain, Avneet Kaur, Rashmi Nagpal, and Ganesh Bagler. FlavorDB: a database of flavor molecules.… [find](https://scholar.google.com/scholar?q=Neelansh+Garg%2C+Apuroop+Sethupathy%2C+Rudraksh+Tuwani%2C+Rakhi+NK%2C+Shubham+Dokania%2C+Arvind+Iyer%2C+Ayushi+Gupta%2C+Shubhra+Agrawal%2C+Navjot+Singh%2C+Shubham+Shukla%2C+Kriti+Kathuria%2C+Rahul+Badhwar%2C+Rakesh+Kanji%2C+An)
69. Andreas Keller and Leslie B. Vosshall. Olfactory perception of chemically diverse molecules. BMC Neuroscience, 17(1), August 2016. [find](https://scholar.google.com/scholar?q=Andreas+Keller+and+Leslie+B%2E+Vosshall%2E+Olfactory+perception+of+chemically+diverse+molecules%2E+BMC+Neuroscience%2C+17%281%29%2C+August+2016%2E)
70. Charles J Wysocki and Avery N Gilbert. National geographic smell survey: Effects of age are heterogenous. Annals of the New York Academy of Sciences, 561(1):12–28, 1989. [find](https://scholar.google.com/scholar?q=Charles+J+Wysocki+and+Avery+N+Gilbert%2E+National+geographic+smell+survey%3A+Effects+of+age+are+heterogenous%2E+Annals+of+the+New+York+Academy+of+Sciences%2C+561%281%29%3A12%E2%80%9328%2C+1989%2E)
71. Aharon Ravia, Kobi Snitz, Danielle Honigstein, Maya Finkel, Rotem Zirler, Ofer Perl, Lavi Secundo, Christophe Laudamiel, David Harel, and Noam Sobel. A measure of smell enables the creation of olfactory metamers. Nature, 588(7836):118–123, November 2020. [find](https://scholar.google.com/scholar?q=Aharon+Ravia%2C+Kobi+Snitz%2C+Danielle+Honigstein%2C+Maya+Finkel%2C+Rotem+Zirler%2C+Ofer+Perl%2C+Lavi+Secundo%2C+Christophe+Laudamiel%2C+David+Harel%2C+and+Noam+Sobel%2E+A+measure+of+smell+enables+the+creation+of+olfacto)
72. Anju Sharma, Bishal Kumar Saha, Rajnish Kumar, and Pritish Kumar Varadwaj. OlfactionBase: a repository to explore odors, odorants, olfactory receptors and odorant–receptor interactions. Nucleic Acids Research, 50(D1):D678–D686, September 2021. [find](https://scholar.google.com/scholar?q=Anju+Sharma%2C+Bishal+Kumar+Saha%2C+Rajnish+Kumar%2C+and+Pritish+Kumar+Varadwaj%2E+OlfactionBase%3A+a+repository+to+explore+odors%2C+odorants%2C+olfactory+receptors+and+odorant%E2%80%93receptor+interactions%2E+Nucleic+Acids+)
73. Kobi Snitz, Adi Yablonka, Tali Weiss, Idan Frumin, Rehan M. Khan, and Noam Sobel. Predicting odor perceptual similarity from odor structure. PLoS Computational Biology, 9(9):e1003184, September 2013. [find](https://scholar.google.com/scholar?q=Kobi+Snitz%2C+Adi+Yablonka%2C+Tali+Weiss%2C+Idan+Frumin%2C+Rehan+M%2E+Khan%2C+and+Noam+Sobel%2E+Predicting+odor+perceptual+similarity+from+odor+structure%2E+PLoS+Computational+Biology%2C+9%289%29%3Ae1003184%2C+September+2013%2E)
74. Kobi Snitz, Ofer Perl, Danielle Honigstein, Lavi Secundo, Aharon Ravia, Adi Yablonka, Yaara Endevelt-Shapira, and Noam Sobel. Smellspace: An odor-based social network as a platform for collecting olfactory perceptual data. Chemical Senses, 44(4):267–278, March 2019. [find](https://scholar.google.com/scholar?q=Kobi+Snitz%2C+Ofer+Perl%2C+Danielle+Honigstein%2C+Lavi+Secundo%2C+Aharon+Ravia%2C+Adi+Yablonka%2C+Yaara+Endevelt%2DShapira%2C+and+Noam+Sobel%2E+Smellspace%3A+An+odor%2Dbased+social+network+as+a+platform+for+collecting+olfa)
75. Elizabeth A Hamel, Jason B Castro, Travis J Gould, Robert Pellegrino, Zhiwei Liang, Liyah A Coleman, Famesh Patel, Derek S Wallace, Tanushri Bhatnagar, Joel D Mainland, et al. Pyrfume: A window to the world’s olfactory data. Scientific Data, 11(1):1220, 2024. [find](https://scholar.google.com/scholar?q=Elizabeth+A+Hamel%2C+Jason+B+Castro%2C+Travis+J+Gould%2C+Robert+Pellegrino%2C+Zhiwei+Liang%2C+Liyah+A+Coleman%2C+Famesh+Patel%2C+Derek+S+Wallace%2C+Tanushri+Bhatnagar%2C+Joel+D+Mainland%2C+et+al%2E+Pyrfume%3A+A+window+to+the)
76. Fanwang Meng, Yang Xi, Jinfeng Huang, and Paul W Ayers. A curated diverse molecular database of blood-brain barrier permeability with chemical descriptors. Scientific Data, 8(1):289, 2021. [find](https://scholar.google.com/scholar?q=Fanwang+Meng%2C+Yang+Xi%2C+Jinfeng+Huang%2C+and+Paul+W+Ayers%2E+A+curated+diverse+molecular+database+of+blood%2Dbrain+barrier+permeability+with+chemical+descriptors%2E+Scientific+Data%2C+8%281%29%3A289%2C+2021%2E)
77. EvE Bio Consortium. Eve Bio pharmome dataset: Data release 3. [https://evebio.org](https://evebio.org), March 2025. Version 3. Publisher: EvE Bio, LLC. License: CC BY-NC-SA 4.0. [↗](https://evebio.org)
78. Cheng Fang, Ye Wang, Richard Grater, Sudarshan Kapadnis, Cheryl Black, Patrick Trapa, and Simone Sciabola. Prospective validation of machine learning algorithms for absorption, distribution, metabolism, and excretion prediction: An industrial perspective. Journal of Chemical Information and Modeling… [find](https://scholar.google.com/scholar?q=Cheng+Fang%2C+Ye+Wang%2C+Richard+Grater%2C+Sudarshan+Kapadnis%2C+Cheryl+Black%2C+Patrick+Trapa%2C+and+Simone+Sciabola%2E+Prospective+validation+of+machine+learning+algorithms+for+absorption%2C+distribution%2C+metabolis)
79. Murat Cihan Sorkun, Abhishek Khetan, and Süleyman Er. AqSolDB, a curated reference set of aqueous solubility and 2D descriptors for a diverse set of compounds. Sci. Data, 6(1):143, August 2019. [find](https://scholar.google.com/scholar?q=Murat+Cihan+Sorkun%2C+Abhishek+Khetan%2C+and+S%C3%BCleyman+Er%2E+AqSolDB%2C+a+curated+reference+set+of+aqueous+solubility+and+2D+descriptors+for+a+diverse+set+of+compounds%2E+Sci%2E+Data%2C+6%281%29%3A143%2C+August+2019%2E)
80. Jonathan Zheng and Olivier Lafontant-Joseph. IUPAC digitized pKa dataset. https://gi thub.com/IUPAC/Dissociation-Constants, 2025. Version: 2025-03-21. Publisher: International Union of Pure and Applied Chemistry (IUPAC). Institution: Green Group, Department of Chemical Engineering, MIT. License: CC… — [doi:10.5281/zenodo](https://doi.org/10.5281/zenodo) [find](https://scholar.google.com/scholar?q=Jonathan+Zheng+and+Olivier+Lafontant%2DJoseph%2E+IUPAC+digitized+pKa+dataset%2E+https%3A%2F%2Fgi+thub%2Ecom%2FIUPAC%2FDissociation%2DConstants%2C+2025%2E+Version%3A+2025%2D03%2D21%2E+Publisher%3A+International+Union+of+Pure+and+Applie)
81. Ryan-Rhys Griffiths, Jake L Greenfield, Aditya R Thawani, Arian R Jamasb, Henry B Moss, Anthony Bourached, Penelope Jones, William McCorkindale, Alexander A Aldrick, Matthew J Fuchter, et al. Data-driven discovery of molecular photoswitches with multioutput Gaussian processes. Chemical Science, 13(4… [find](https://scholar.google.com/scholar?q=Ryan%2DRhys+Griffiths%2C+Jake+L+Greenfield%2C+Aditya+R+Thawani%2C+Arian+R+Jamasb%2C+Henry+B+Moss%2C+Anthony+Bourached%2C+Penelope+Jones%2C+William+McCorkindale%2C+Alexander+A+Aldrick%2C+Matthew+J+Fuchter%2C+et+al%2E+Data%2Ddri)
82. Lars Ruddigkeit, Ruud Van Deursen, Lorenz C Blum, and Jean-Louis Reymond. Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. Journal of Chemical Information and Modeling, 52(11):2864–2875, 2012. [find](https://scholar.google.com/scholar?q=Lars+Ruddigkeit%2C+Ruud+Van+Deursen%2C+Lorenz+C+Blum%2C+and+Jean%2DLouis+Reymond%2E+Enumeration+of+166+billion+organic+small+molecules+in+the+chemical+universe+database+GDB%2D17%2E+Journal+of+Chemical+Information+a)
83. RDKit: Open-source cheminformatics. [http://www.rdkit.org](http://www.rdkit.org). [Online; accessed 27-January-2025]. [↗](http://www.rdkit.org)
84. Geemi P Wellawatte, Aditi Seshadri, and Andrew D White. Model agnostic generation of counterfactual explanations for molecules. Chemical Science, 13(13):3697–3705, 2022. [find](https://scholar.google.com/scholar?q=Geemi+P+Wellawatte%2C+Aditi+Seshadri%2C+and+Andrew+D+White%2E+Model+agnostic+generation+of+counterfactual+explanations+for+molecules%2E+Chemical+Science%2C+13%2813%29%3A3697%E2%80%933705%2C+2022%2E)
85. Edwin A Hill. On a system of indexing chemical literature; adopted by the classification division of the US patent office. Journal of the American Chemical Society, 22(8):478–494, 1900. [find](https://scholar.google.com/scholar?q=Edwin+A+Hill%2E+On+a+system+of+indexing+chemical+literature%3B+adopted+by+the+classification+division+of+the+US+patent+office%2E+Journal+of+the+American+Chemical+Society%2C+22%288%29%3A478%E2%80%93494%2C+1900%2E)
86. David Rogers and Mathew Hahn. Extended-connectivity fingerprints. Journal of Chemical Information and Modeling, 50(5):742–754, 2010. [find](https://scholar.google.com/scholar?q=David+Rogers+and+Mathew+Hahn%2E+Extended%2Dconnectivity+fingerprints%2E+Journal+of+Chemical+Information+and+Modeling%2C+50%285%29%3A742%E2%80%93754%2C+2010%2E)
87. Sunghwan Kim, Paul A Thiessen, Evan E Bolton, Jie Chen, Gang Fu, Asta Gindulyte, Lianyi Han, Jane He, Siqian He, Benjamin A Shoemaker, et al. PubChem substance and compound databases. Nucleic Acids Research, 44(D1):D1202–D1213, 2016. [find](https://scholar.google.com/scholar?q=Sunghwan+Kim%2C+Paul+A+Thiessen%2C+Evan+E+Bolton%2C+Jie+Chen%2C+Gang+Fu%2C+Asta+Gindulyte%2C+Lianyi+Han%2C+Jane+He%2C+Siqian+He%2C+Benjamin+A+Shoemaker%2C+et+al%2E+PubChem+substance+and+compound+databases%2E+Nucleic+Acids+Re)
88. Sunghwan Kim, Jie Chen, Tiejun Cheng, Asta Gindulyte, Jia He, Siqian He, Qingliang Li, Benjamin A Shoemaker, Paul A Thiessen, Bo Yu, et al. PubChem 2019 update: improved access to chemical data. Nucleic Acids Research, 47(D1):D1102–D1109, 2019. [find](https://scholar.google.com/scholar?q=Sunghwan+Kim%2C+Jie+Chen%2C+Tiejun+Cheng%2C+Asta+Gindulyte%2C+Jia+He%2C+Siqian+He%2C+Qingliang+Li%2C+Benjamin+A+Shoemaker%2C+Paul+A+Thiessen%2C+Bo+Yu%2C+et+al%2E+PubChem+2019+update%3A+improved+access+to+chemical+data%2E+Nucle)
89. Sunghwan Kim, Jie Chen, Tiejun Cheng, Asta Gindulyte, Jia He, Siqian He, Qingliang Li, Benjamin A Shoemaker, Paul A Thiessen, Bo Yu, et al. PubChem 2023 update. Nucleic Acids Research, 51(D1):D1373–D1380, 2023. [find](https://scholar.google.com/scholar?q=Sunghwan+Kim%2C+Jie+Chen%2C+Tiejun+Cheng%2C+Asta+Gindulyte%2C+Jia+He%2C+Siqian+He%2C+Qingliang+Li%2C+Benjamin+A+Shoemaker%2C+Paul+A+Thiessen%2C+Bo+Yu%2C+et+al%2E+PubChem+2023+update%2E+Nucleic+Acids+Research%2C+51%28D1%29%3AD1373%E2%80%93D1)
90. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. [Training language models to follow instructions with human feedback](https://md.research.elamur.ai/free/en/papers/ouyang-2022-training-language-models-follow-instructions/). Advances in Neural Information Processing Systems, 35:27730–27744, 2022.
91. Thomas Anthony, Zheng Tian, and David Barber. [Thinking fast and slow with deep learning and tree search](https://md.research.elamur.ai/free/en/papers/anthony-2017-thinking-fast-slow-deep-learning/). In Proceedings of the 31st International Conference on Neural Information Processing Systems, pages 5366–5376, 2017.
92. Alex Havrilla, Yuqing Du, Sharath Chandra Raparthy, Christoforos Nalmpantis, Jane Dwivedi-Yu, Maksym Zhuravinskyi, Eric Hambro, Sainbayar Sukhbaatar, and Roberta Raileanu. [Teaching large language models to reason with reinforcement learning](https://md.research.elamur.ai/free/en/papers/havrilla-2024-teaching-large-language-models-reason/), 2024.
93. Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. [Distilling the knowledge in a neural network](https://md.research.elamur.ai/free/en/papers/hinton-2015-distilling-knowledge-neural-network/), 2015.
94. John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347, 2017. [find](https://scholar.google.com/scholar?q=John+Schulman%2C+Filip+Wolski%2C+Prafulla+Dhariwal%2C+Alec+Radford%2C+and+Oleg+Klimov%2E+Proximal+policy+optimization+algorithms%2E+arXiv+preprint+arXiv%3A1707%2E06347%2C+2017%2E)
95. Marah Abdin, Jyoti Aneja, Harkirat Behl, Sébastien Bubeck, Ronen Eldan, Suriya Gunasekar, Michael Harrison, Russell J. Hewett, Mojan Javaheripi, Piero Kauffmann, James R. Lee, Yin Tat Lee, Yuanzhi Li, Weishung Liu, Caio C. T. Mendes, Anh Nguyen, Eric Price, Gustavo de Rosa, Olli Saarikivi, Adil Sali… — [Phi-4 Technical Report](https://md.research.elamur.ai/free/en/papers/abdin-2024-phi-4-technical-report/)
96. DeepSeek-AI, Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, Damai Dai, Daya Guo, Dejian Yang, Deli Chen, Dongjie Ji, Erhang Li, Fangyun Lin, Fucong Dai, Fuli Luo, Guangbo Hao, Guanting Chen, Guowei Li, H. Zhang, Han Bao, H… [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2C+Aixin+Liu%2C+Bei+Feng%2C+Bing+Xue%2C+Bingxuan+Wang%2C+Bochao+Wu%2C+Chengda+Lu%2C+Chenggang+Zhao%2C+Chengqi+Deng%2C+Chenyu+Zhang%2C+Chong+Ruan%2C+Damai+Dai%2C+Daya+Guo%2C+Dejian+Yang%2C+Deli+Chen%2C+Dongjie+Ji%2C+Erhan)
97. Mistral AI. mistralai/mistral-small-24b-instruct-2501, 2025. Accessed April 22, 2025. [find](https://scholar.google.com/scholar?q=Mistral+AI%2E+mistralai%2Fmistral%2Dsmall%2D24b%2Dinstruct%2D2501%2C+2025%2E+Accessed+April+22%2C+2025%2E)
98. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Tiantian Fan, Gaohong Liu, Lingjun Liu, Xin Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Guangming Sheng, Yuxuan Tong, Chi Zhang, Mofan Zhang, Wang Zhang, Hang Zhu, Jinhua Zhu, Jiaze Chen, Jiangjie Chen, Chengyi Wang, Hongli Yu, Weinan D… — [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/)
99. Yiping Wang, Qing Yang, Zhiyuan Zeng, Liliang Ren, Lucas Liu, Baolin Peng, Hao Cheng, Xuehai He, Kuan Wang, Jianfeng Gao, Weizhu Chen, Shuohang Wang, Simon Shaolei Du, and Yelong Shen. [Reinforcement learning for reasoning in large language models with one training example](https://md.research.elamur.ai/free/en/papers/wang-2025-reinforcement-learning-reasoning-large-language/), 2025.
100. Nikhil Chandak, Shashwat Goel, and Ameya Prabhu. Incorrect baseline evaluations call into question recent llm-rl claims. [https://safe-lip-9a8.notion.site/Incorrect-Bas](https://safe-lip-9a8.notion.site/Incorrect-Bas) eline-Evaluations-Call-into-Question-Recent-LLM-RL-Claims-2012f1fbf0e e8094ab8ded1953c15a37?pvs=4, 2025. Notion Blog. [↗](https://safe-lip-9a8.notion.site/Incorrect-Bas)
101. Wengong Jin, Connor W Coley, Regina Barzilay, and Tommi Jaakkola. Predicting organic reaction outcomes with Weisfeiler-Lehman network. In Proceedings of the 31st International Conference on Neural Information Processing Systems, pages 2604–2613, 2017. [find](https://scholar.google.com/scholar?q=Wengong+Jin%2C+Connor+W+Coley%2C+Regina+Barzilay%2C+and+Tommi+Jaakkola%2E+Predicting+organic+reaction+outcomes+with+Weisfeiler%2DLehman+network%2E+In+Proceedings+of+the+31st+International+Conference+on+Neural+Inf)
102. John Schulman. Approximating KL divergence. Blog post, 2020. Accessed: 2025-02-01. [find](https://scholar.google.com/scholar?q=John+Schulman%2E+Approximating+KL+divergence%2E+Blog+post%2C+2020%2E+Accessed%3A+2025%2D02%2D01%2E)
103. Markus Hartenfeller, Martin Eberle, Peter Meier, Cristina Nieto-Oberhuber, Karl-Heinz Altmann, Gisbert Schneider, Edgar Jacoby, and Steffen Renner. A collection of robust organic synthesis reactions for in silico molecule design. Journal of Chemical Information and Modeling, 51(12):3093–3098, 2011. [find](https://scholar.google.com/scholar?q=Markus+Hartenfeller%2C+Martin+Eberle%2C+Peter+Meier%2C+Cristina+Nieto%2DOberhuber%2C+Karl%2DHeinz+Altmann%2C+Gisbert+Schneider%2C+Edgar+Jacoby%2C+and+Steffen+Renner%2E+A+collection+of+robust+organic+synthesis+reactions+f)
104. Pat Walters. Mining ring systems in molecules for fun and profit. https://practicalche minformatics.blogspot.com/2022/12/mining-ring-systems-in-molecules-for .html, 2022. Accessed: 2025-05-08. [find](https://scholar.google.com/scholar?q=Pat+Walters%2E+Mining+ring+systems+in+molecules+for+fun+and+profit%2E+https%3A%2F%2Fpracticalche+minformatics%2Eblogspot%2Ecom%2F2022%2F12%2Fmining%2Dring%2Dsystems%2Din%2Dmolecules%2Dfor+%2Ehtml%2C+2022%2E+Accessed%3A+2025%2D05%2D08%2E)
105. Peter Ertl, Steven Jelfs, Johannes Mühlbacher, Ansgar Schuffenhauer, and Paul Selzer. Quest for the rings: In silico exploration of ring universe to identify novel bioactive heteroaromatic scaffolds. Journal of Medicinal Chemistry, 49(15):4568–4573, 2006. [find](https://scholar.google.com/scholar?q=Peter+Ertl%2C+Steven+Jelfs%2C+Johannes+M%C3%BChlbacher%2C+Ansgar+Schuffenhauer%2C+and+Paul+Selzer%2E+Quest+for+the+rings%3A+In+silico+exploration+of+ring+universe+to+identify+novel+bioactive+heteroaromatic+scaffolds%2E+)
106. Pat Walters. useful_rdkit_utils: RDKit utility functions. [https://github.com/PatWalter](https://github.com/PatWalter) s/useful_rdkit_utils. Accessed: 2025-05-08. [↗](https://github.com/PatWalter)
107. G Richard Bickerton, Gaia V Paolini, Jérémy Besnard, Sorel Muresan, and Andrew L Hopkins. Quantifying the chemical beauty of drugs. Nature Chemistry, 4(2):90–98, 2012. [find](https://scholar.google.com/scholar?q=G+Richard+Bickerton%2C+Gaia+V+Paolini%2C+J%C3%A9r%C3%A9my+Besnard%2C+Sorel+Muresan%2C+and+Andrew+L+Hopkins%2E+Quantifying+the+chemical+beauty+of+drugs%2E+Nature+Chemistry%2C+4%282%29%3A90%E2%80%9398%2C+2012%2E)
108. Samyam Rajbhandari, Jeff Rasley, Olatunji Ruwase, and Yuxiong He. ZeRO: Memory optimizations toward training trillion parameter models. In SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pages 1–16. IEEE, 2020. [find](https://scholar.google.com/scholar?q=Samyam+Rajbhandari%2C+Jeff+Rasley%2C+Olatunji+Ruwase%2C+and+Yuxiong+He%2E+ZeRO%3A+Memory+optimizations+toward+training+trillion+parameter+models%2E+In+SC20%3A+International+Conference+for+High+Performance+Computing)
109. Gabriele Libardi, Gianni De Fabritiis, and Sebastian Dittert. Guided exploration with proximal policy optimization using a single demonstration. In Marina Meila and Tong Zhang, editors, Proceedings of the 38th International Conference on Machine Learning, volume 139 of Proceedings of Machine Learnin… [find](https://scholar.google.com/scholar?q=Gabriele+Libardi%2C+Gianni+De+Fabritiis%2C+and+Sebastian+Dittert%2E+Guided+exploration+with+proximal+policy+optimization+using+a+single+demonstration%2E+In+Marina+Meila+and+Tong+Zhang%2C+editors%2C+Proceedings+of)
110. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, et al. [The Llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). arXiv preprint arXiv:2407.21783, 2024.
111. Yuyan Liu, Sirui Ding, Sheng Zhou, Wenqi Fan, and Qiaoyu Tan. MolecularGPT: Open large language model (LLM) for few-shot molecular property prediction. arXiv [q-bio.QM], June 2024. [find](https://scholar.google.com/scholar?q=Yuyan+Liu%2C+Sirui+Ding%2C+Sheng+Zhou%2C+Wenqi+Fan%2C+and+Qiaoyu+Tan%2E+MolecularGPT%3A+Open+large+language+model+%28LLM%29+for+few%2Dshot+molecular+property+prediction%2E+arXiv+%5Bq%2Dbio%2EQM%5D%2C+June+2024%2E)
112. Christopher Fifty, Jure Leskovec, and Sebastian Thrun. In-context learning for few-shot molecular property prediction. arXiv [cs.LG], October 2023. [find](https://scholar.google.com/scholar?q=Christopher+Fifty%2C+Jure+Leskovec%2C+and+Sebastian+Thrun%2E+In%2Dcontext+learning+for+few%2Dshot+molecular+property+prediction%2E+arXiv+%5Bcs%2ELG%5D%2C+October+2023%2E)
113. Johannes Schimunek, Sohvi Luukkonen, and Günter Klambauer. MHNfs: Prompting in-context bioactivity predictions for low-data drug discovery. Journal of Chemical Information and Modeling, April 2025. [find](https://scholar.google.com/scholar?q=Johannes+Schimunek%2C+Sohvi+Luukkonen%2C+and+G%C3%BCnter+Klambauer%2E+MHNfs%3A+Prompting+in%2Dcontext+bioactivity+predictions+for+low%2Ddata+drug+discovery%2E+Journal+of+Chemical+Information+and+Modeling%2C+April+2025%2E)
114. Jiatong Li, Wei Liu, Zhihao Ding, Wenqi Fan, Yuqiang Li, and Qing Li. Large language models are in-context molecule learners. IEEE Transactions on Knowledge and Data Engineering, 2025. [find](https://scholar.google.com/scholar?q=Jiatong+Li%2C+Wei+Liu%2C+Zhihao+Ding%2C+Wenqi+Fan%2C+Yuqiang+Li%2C+and+Qing+Li%2E+Large+language+models+are+in%2Dcontext+molecule+learners%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2C+2025%2E)
115. Xianggen Liu, Yan Guo, Haoran Li, Jin Liu, Shudong Huang, Bowen Ke, and Jiancheng Lv. DrugLLM: Open large language model for few-shot molecule generation. arXiv [q-bio.BM], May 2024. [find](https://scholar.google.com/scholar?q=Xianggen+Liu%2C+Yan+Guo%2C+Haoran+Li%2C+Jin+Liu%2C+Shudong+Huang%2C+Bowen+Ke%2C+and+Jiancheng+Lv%2E+DrugLLM%3A+Open+large+language+model+for+few%2Dshot+molecule+generation%2E+arXiv+%5Bq%2Dbio%2EBM%5D%2C+May+2024%2E)
116. Lei Shi, Zhimeng Liu, Yi Yang, Weize Wu, Yuyang Zhang, Hongbo Zhang, Jing Lin, Siyu Wu, Zihan Chen, Ruiming Li, Nan Wang, Zipeng Liu, Huobin Tan, Hongyi Gao, Yue Zhang, and Ge Wang. LLM-based MOFs synthesis condition extraction using few-shot demonstrations. arXiv [cs.CL], August 2024. [find](https://scholar.google.com/scholar?q=Lei+Shi%2C+Zhimeng+Liu%2C+Yi+Yang%2C+Weize+Wu%2C+Yuyang+Zhang%2C+Hongbo+Zhang%2C+Jing+Lin%2C+Siyu+Wu%2C+Zihan+Chen%2C+Ruiming+Li%2C+Nan+Wang%2C+Zipeng+Liu%2C+Huobin+Tan%2C+Hongyi+Gao%2C+Yue+Zhang%2C+and+Ge+Wang%2E+LLM%2Dbased+MOFs+syn)

*Updated 3 November 2026*