arXiv AI October 26, 2026 By Yifei Wang, Botian Wang, YiFei Wang, Jiangtao Feng, Xinbo Zhang, Yawen Ouyang, Yixin Wu, Lihao Wang, Xiaoqing Zheng, Xuanjing Huang, Hao Zhou

Solvent: Long-Horizon Reasoning for Multi-Step Retrosynthesis

Read the original on arXiv AI →

Solvent is an 8‑billion‑parameter large language model designed for long‑horizon reasoning in multi‑step retrosynthesis. It learns to interleave synthesis planning, external availability checks, and adaptive route revision through a two‑round post‑training curriculum. Experiments show a 2.1× performance boost from reinforcement learning, achieving 61.86% accuracy across four benchmarks and outperforming mid‑scale language models and prior search‑based systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 17

RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning

arXiv:2607. 14512v1 Announce Type: new Abstract: Multi-step retrosynthesis planning seeks to decompose a target molecule into commercially available building blocks through a sequence of feasible reactions.

By Yanqiao Zhu, Jingru Gan, Xiaoqi Sun, Fang Sun, Yidan Shi, Md Mofijul Islam, Chao Shang, Wenhao Gao, Connor W. Coley, Yizhou Sun, Wei Wang

llms agents benchmarks

arXiv AI

Aug 25

RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning

arXiv:2507.17448v2 Announce Type: replace-cross Abstract: Retrosynthetic planning is a cornerstone of organic synthesis and drug discovery. Yet existing AI methods often rely on pattern matching rath...

By Situo Zhang, Hanqi Li, Lu Chen, Zihan Zhao, Xuanze Lin, Zichen Zhu, Danyu Luo, Bo Chen, Xin Chen, Kai Yu

llms reinforcement-learning benchmarks safety

arXiv AI

Jun 9

RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction

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

llms reinforcement-learning fine-tuning

arXiv AI

Aug 20

Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis

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

llms fine-tuning benchmarks

arXiv AI

Jul 7

URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment

arXiv:2607. 04688v1 Announce Type: cross Abstract: Synthesis planning aiming to find pathways of reactions for a target molecule is one of the most important and challenging tasks in drug discovery.

By Bogdan Zagribelnyy, Ivan Ilin, Nikita Bondarev, Anton Morgunov, Arkadii Lin, Maksim Kuznetsov, Rim Shayakhmetov, Vladimir Aladinskiy, Alex Aliper, Alex Zhavoronkov

llms benchmarks

arXiv AI

Sep 18

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning

oMeBench is a large-scale, expert-curated benchmark designed to evaluate large language models (LLMs) on organic mechanism reasoning. It contains over 10,000 annotated mechanistic steps, including reaction type labels, intermediate structures, and difficulty ratings, and introduces the oMeS scoring framework to assess logical consistency and chemical structural similarity. Evaluation shows that while current LLMs display promising chemical intuition, they often fail to produce correct and consistent multi-step reasoning, though prompting and fine-tuning can bring smaller models up to the level of closed‑source frontier models.

By Ruiling Xu, Yifan Zhang

llms fine-tuning benchmarks

One email a morning, machine-written

Related stories

RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning

RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning

RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction

Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis

URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment

oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning