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:2606. 01220v1 Announce Type: cross Abstract: Generating molecules that simultaneously satisfy drug-like properties and conform to the 3D structure of a target protein is a core challenge in structure-based drug design (SBDD).
By Guang Lin, Shikui Tu, Lei Xu
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:2603. 10395v2 Announce Type: replace Abstract: Graph generation is a fundamental task with broad applications, such as drug discovery.
By Baoheng Zhu, Deyu Bo, Delvin Ce Zhang, Xiao Wang
arXiv:2606. 11256v1 Announce Type: cross Abstract: Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes.
By C\'esar Ojeda, Darius A. Faroughy, Maryam Karimi, Payam Zarrintaj, Mir Mehdi Seyedebrahimi, Mart\'in Carballo-Pacheco
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