Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models

• URL: http://arxiv.org/abs/2607.12771v2
• Date: Thu, 16 Jul 2026 00:41:49 GMT
• Title: Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models
• Abstract summary: We build a novel, large-scale reasoning dataset of reaction mechanisms.<n>We rigorously evaluate model performance on hierarchical mechanism reasoning.<n>Our fine-tuned Qwen3-30B-A3B achieves 8.3% exact pathway match on FukuyamaBench SetA, surpassing the specialized FlowER model (5.1%)
• Score: 3.2985641852325056
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reaction mechanisms consist of the step-by-step sequences of elementary reactions that explain chemical transformations. Learning the mechanism logic is therefore essential for enhancing the fundamental chemical intelligence of large language models (LLMs). The stepwise deduction of reaction mechanism aligns naturally with the reasoning paradigms of reasoning LLMs. However, current chemical LLMs primarily emphasize coarse-grained name reactions for product prediction and retrosynthesis, often leading to physical inconsistencies and hallucinations. In contrast, specialized small-scale generative models for mechanism inference typically suffer from restricted generalization capacity across diverse chemical spaces. To overcome these limitations, we built a novel, large-scale reasoning dataset of reaction mechanisms. Furthermore, we established the FukuyamaBench, a difficult benchmark derived from Fukuyama's Advanced Organic Reaction Mechanism book, to rigorously evaluate model performance on hierarchical mechanism reasoning. Our fine-tuned Qwen3-30B-A3B achieves 8.3% exact pathway match on FukuyamaBench Set~A, surpassing the specialized FlowER model (5.1%), demonstrating that mechanism-aware training substantially enhances chemical reasoning in language models.

Related papers

• Autonomous Chemical Mechanistic Discovery through Agentic Reasoning and Validation [46.063922326510855]
  ARCHE is an autonomous agentic system that integrates a general-purpose reasoning model, a domain-specialized computational chemistry model, and a structured tool registry.<n>It interprets scientific questions, generates mechanistic hypotheses, orchestrates computational selectivity, and iteratively refines conclusions based on computed evidence.<n>By coupling agentic reasoning with rigorous computational validation, ARCHE advances autonomous mechanistic discovery and establishes a foundation for broader machine-assisted chemical research.
  arXiv  Detail & Related papers  (2026-09-10T06:49:24Z)
• Chem4DLLM: 4D Multimodal LLMs for Chemical Dynamics Understanding [52.499532583297885]
  ChemDU translates 4D molecular trajectories into interpretable natural-language explanations.<n>ChemDU focuses on fundamental dynamic scenarios, including gas-phase and catalytic reactions.<n>Chem4DBench is the first dataset pairing 4D molecular trajectories with expert-authored explanations.
  arXiv  Detail & Related papers  (2026-03-12T13:36:58Z)
• RxnNano:Training Compact LLMs for Chemical Reaction and Retrosynthesis Prediction via Hierarchical Curriculum Learning [20.904697361501174]
  We argue that the core challenge lies in instilling these knowledge into the models.<n>We propose a unified framework that prioritizes chemical understanding over scale through three key innovations.
  arXiv  Detail & Related papers  (2026-02-10T07:42:23Z)
• Teaching Language Models Mechanistic Explainability Through Arrow-Pushing [3.488381738536745]
  Chemical reaction mechanisms provide crucial insight into synthesizability.<n>Current Computer-Assisted Synthesis Planning (CASP) systems lack mechanistic grounding.<n>We introduce a computational framework for teaching language models to predict chemical reaction mechanisms.
  arXiv  Detail & Related papers  (2025-12-05T13:57:50Z)
• oMeBench: Towards Robust Benchmarking of LLMs in Organic Mechanism Elucidation and Reasoning [44.36582860924775]
  We introduce oMeBench, the first large-scale, expert-curated benchmark for organic mechanism reasoning in organic chemistry.<n>We also propose oMeS, a dynamic evaluation framework that combines step-level logic and chemical similarity.
  arXiv  Detail & Related papers  (2025-10-09T03:13:31Z)
• Learning Chemical Reaction Representation with Reactant-Product Alignment [50.28123475356234]
  RAlign is a novel chemical reaction representation learning model for various organic reaction-related tasks.<n>By integrating atomic correspondence between reactants and products, our model discerns the molecular transformations that occur during the reaction.<n>We introduce a reaction-center-aware attention mechanism that enables the model to concentrate on key functional groups.
  arXiv  Detail & Related papers  (2024-11-26T17:41:44Z)
• ReactAIvate: A Deep Learning Approach to Predicting Reaction Mechanisms and Unmasking Reactivity Hotspots [4.362338454684645]
  We develop an interpretable attention-based GNN that achieved near-unity and 96% accuracy for reaction step classification. Our model adeptly identifies key atom(s) even from out-of-distribution classes. This generalizabilty allows for the inclusion of new reaction types in a modular fashion, thus will be of value to experts for understanding the reactivity of new molecules.
  arXiv  Detail & Related papers  (2024-07-14T05:53:18Z)
• Beyond Major Product Prediction: Reproducing Reaction Mechanisms with Machine Learning Models Trained on a Large-Scale Mechanistic Dataset [10.968137261042715]
  Mechanistic understanding of organic reactions can facilitate reaction development, impurity prediction, and in principle, reaction discovery. While several machine learning models have sought to address the task of predicting reaction products, their extension to predicting reaction mechanisms has been impeded by the lack of a corresponding mechanistic dataset. We construct such a dataset by imputing intermediates between experimentally reported reactants and products using expert reaction templates and train several machine learning models on the resulting dataset of 5,184,184 elementary steps.
  arXiv  Detail & Related papers  (2024-03-07T15:26:23Z)
• AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning [45.379791270351184]
  RMechRP is a new deep learning-based reaction predictor system. We develop and train models using RMechDB, a public database of radical reactions. Our results demonstrate the effectiveness of RMechRP in providing accurate and interpretable predictions.
  arXiv  Detail & Related papers  (2023-11-02T09:47:27Z)
• Improving Molecular Representation Learning with Metric Learning-enhanced Optimal Transport [49.237577649802034]
  We develop a novel optimal transport-based algorithm termed MROT to enhance their generalization capability for molecular regression problems. MROT significantly outperforms state-of-the-art models, showing promising potential in accelerating the discovery of new substances.
  arXiv  Detail & Related papers  (2022-02-13T04:56:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.