# A Scientific Reasoning Model for Organic Synthesis Procedure Generation

arXiv: https://arxiv.org/abs/2512.13668 · HTML: https://mlsanity.com/paper/2512.13668/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 25 of its 104 references that are in the map.
- First posted on arXiv 15 Dec 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 25 of 25)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Reinforcement Learning for Reasoning in Large Language Models with One Training Example](https://mlsanity.com/paper/2504.20571/) (2025)
- [Phi-4-reasoning Technical Report](https://mlsanity.com/paper/2504.21318/) (2025)
- [Token-level Direct Preference Optimization](https://mlsanity.com/paper/2404.11999/) (2024)
- [Training a Scientific Reasoning Model for Chemistry](https://mlsanity.com/paper/2506.17238/) (2025)
- [Beyond Chemical QA: Evaluating LLM's Chemical Reasoning with Modular Chemical Operations](https://mlsanity.com/paper/2505.21318/) (2025)
- [Nature Language Model: Deciphering the Language of Nature for Scientific Discovery](https://mlsanity.com/paper/2502.07527/) (2025)
- [ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge](https://mlsanity.com/paper/2507.21990/) (2025)
- [ReactXT: Understanding Molecular "Reaction-ship" via Reaction-Contextualized Molecule-Text Pretraining](https://mlsanity.com/paper/2405.14225/) (2024)
- [Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidation](https://mlsanity.com/paper/2503.08537/) (2025)
- [Chem-R: Learning to Reason as a Chemist](https://mlsanity.com/paper/2510.16880/) (2025)
- [Retro-fallback: retrosynthetic planning in an uncertain world](https://mlsanity.com/paper/2310.09270/) (2023)
- [MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs](https://mlsanity.com/paper/2508.02066/) (2025)
- [FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models](https://mlsanity.com/paper/2508.01055/) (2025)
- [SUPERChem: A Multimodal Reasoning Benchmark in Chemistry](https://mlsanity.com/paper/2512.01274/) (2025)
- [ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data](https://mlsanity.com/paper/2506.23520/) (2025)

## Abstract (arXiv)

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.