The paper explores how large language models (LLMs) can be trained for small-molecule drug design by using synthetic tasks that are cheaper to evaluate. By employing a curriculum that gradually increases task difficulty, the authors demonstrate that LLMs can learn design strategies that outperform larger models on structure-based lead optimization. This approach shows that scaling post‑training with synthetic tasks can effectively adapt LLMs to high‑cost experimental scenarios that are otherwise infeasible to train on directly.
By Frank Hu, Shriram Chennakesavalu, Zichen Wang, Patricia Suriana, Bodhi Vani, Kirill Shmilovich, Kangway Chuang, Colin Grambow
arXiv:2607. 19044v1 Announce Type: new Abstract: Leveraging large language models (LLMs) for molecular generation has shown remarkable potential in chemical and drug design.
By Mingxuan Ouyang, Hao Lan, Wanyu Lin
arXiv:2603. 12666v2 Announce Type: replace-cross Abstract: Retrosynthesis prediction aims to identify reactants that can synthesize a given product molecule.
By Hanbum Ko, Chanhui Lee, Ye Rin Kim, Rodrigo Hormazabal, Sehui Han, Sungbin Lim, Sungwoong Kim
RePro is a web‑recycling technique that trains a small language model (as little as 1 B parameters) with reinforcement learning to produce high‑quality, faithful rephrasings of pretraining data. The method uses one quality reward and three faithfulness rewards to preserve core semantics and structure while converting organic data into better training examples. Experiments show that RePro boosts downstream accuracy by 3.7–14.5 % over organic‑only baselines and improves data efficiency 2–3×, outperforming prior prompting‑based recycling approaches.
By Zichun Yu, Chenyan Xiong
The paper introduces LM2LM, a method that trains large language models (LLMs) to propose improvements for other LLMs using reinforcement learning (RL). It employs a frozen research world model (RWM) to predict the gains of proposals, providing a cheaper surrogate reward, and periodically validates high‑scoring proposals to keep feedback reliable. Experiments across eight LM development environments show that LM2LM enables a Qwen3.8‑27B model to outperform GPT‑6‑sol on held‑out tasks while reducing data‑generation cost by 33%, and it generalizes to unseen model families.
By Minhua Lin, Zijun Wang, Zewen Liu, Zhaotian Weng, Bing He, Zhan Shi, Benoit Dumoulin, Xiang Zhang, Suhang Wang, Hanqing Lu
The paper introduces Top‑K prompting as a training and inference strategy to better capture the diverse, plausible predictions inherent in single‑step retrosynthesis. Using an ultra‑large dataset (CREED‑CCV‑2+USPTO‑XL) of ~45.6 million verified reactions, the authors train the Chemistry Constraint‑Consistent Language Model (C3LM). With fine‑tuning that incorporates ChemCensor‑based and novelty‑oriented rewards, C3LM achieves state‑of‑the‑art performance on the OOD URSA‑expert‑2026 benchmark and demonstrates complementary reaction space exploration compared to conventional models, suggesting benefits for ensemble‑based retrosynthesis systems.
By Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Maksim Kuznetsov, Mathieu Reymond, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov
arXiv:2605. 15354v2 Announce Type: replace Abstract: Despite the success of foundation models in language and vision, molecular graph generation still lacks a unified framework for heterogeneous design tasks with reliable controllability.
By Yihan Zhu, Yuhan Liu, Weijiang Li, Tengfei Luo, Meng Jiang
TrajEvolve introduces a trajectory evolution paradigm with hindsight credit assignment to improve reinforcement learning for large language models on long-horizon tasks. It refines low-quality steps in historical trajectories to expose the policy to high-quality compositions that are rarely sampled, and reformulates step-level continuous credit assignment as a binary classification problem to identify redundant steps. Experiments on two datasets show that this approach outperforms existing methods.
By Yi Wen, Hao Chen, Wanyu Wang, Maolin Wang, Pengyue Jia, Derong Xu, Huize Tan, Yingyi Zhang, Wenlin Zhang, Weihong Luo, Xiku Du, Xiangyu Zhao
PGFS++ is a synthesis‑aware reinforcement learning framework that improves molecular properties while ensuring the resulting molecules can be synthesized and remain structurally similar to the input. It builds on PGFS+ by using trainable embedding lookup tables for reaction templates and second reactants, a more effective scoring function, and a refined RL algorithm. Experiments demonstrate that PGFS++ enhances target properties and preserves high output diversity, overcoming the reward‑hacking failure mode seen in earlier versions.
By Boqiao Zhang, Godbless James, Sai Krishna Gottipati, Andrew Fitzgibbon
PGFS++ is a synthesis‑aware reinforcement learning framework that improves molecular properties such as drug‑likeness or binding affinity while ensuring the resulting molecules can be synthesized and remain structurally similar to the input. It builds on PGFS+ by using trainable embedding lookup tables for reaction templates and second reactants, a more effective scoring function, and a refined RL algorithm. The method addresses a reward‑hacking failure mode by treating each input molecule as the start of a forward‑synthesis trajectory, applying learned reaction templates with in‑stock building blocks, and producing diverse, high‑quality outputs with explicit synthesis routes.
arXiv:2606. 24990v1 Announce Type: new Abstract: Reinforcement Learning (RL) has become a powerful paradigm for de novo molecular design, enabling Chemical Language Models (CLMs) to navigate and explore the chemical space while optimizing specific desired properties.
By Borja Medina, Jon Paul Janet
arXiv:2608. 03875v1 Announce Type: cross Abstract: Designing effective reward functions remains a major bottleneck in Reinforcement Learning (RL).
By Pyrros Koussios, Chenhao Li, Xin Chen, Andreas Krause