A Scientific Reasoning Model for Organic Synthesis Procedure Generation

TL;DR

This paper introduces QFANG, a scientific reasoning model that generates detailed experimental procedures for chemical synthesis from reaction equations, integrating chemical knowledge and reasoning to improve automated synthesis planning.

Contribution

The paper presents QFANG, a novel language model with a Chemistry-Guided Reasoning framework, trained on a large dataset, capable of producing accurate, structured synthesis procedures with chain-of-thought reasoning.

Findings

QFANG outperforms baseline models in accuracy and relevance.

The model generalizes to some out-of-domain reactions.

Reinforcement learning further improves procedural accuracy.

Abstract

Solving computer-aided synthesis planning is essential for enabling fully automated, robot-assisted synthesis workflows and improving the efficiency of drug discovery. A key challenge, however, is bridging the gap between computational route design and practical laboratory execution, particularly the accurate prediction of viable experimental procedures for each synthesis step. In this work, we present QFANG, a scientific reasoning language model capable of generating precise, structured experimental procedures directly from reaction equations, with explicit chain-of-thought reasoning. To develop QFANG, we curated a high-quality dataset comprising 905,990 chemical reactions paired with structured action sequences, extracted and processed from patent literature using large language models. We introduce a Chemistry-Guided Reasoning (CGR) framework that produces chain-of-thought data grounded in chemical knowledge at scale. The model subsequently undergoes supervised fine-tuning to elicit complex chemistry reasoning. Finally, we apply Reinforcement Learning from Verifiable Rewards (RLVR) to further enhance procedural accuracy. Experimental results demonstrate that QFANG outperforms advanced general-purpose reasoning models and nearest-neighbor retrieval baselines, measured by traditional NLP similarity metrics and a chemically aware evaluator using an LLM-as-a-judge. Moreover, QFANG generalizes to certain out-of-domain reaction classes and adapts to variations in laboratory conditions and user-specific constraints. We believe that QFANG's ability to generate high-quality synthesis procedures represents an important step toward bridging the gap between computational synthesis planning and fully automated laboratory synthesis.