RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction

• URL: http://arxiv.org/abs/2603.12666v1
• Date: Fri, 13 Mar 2026 05:20:56 GMT
• Title: RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction
• Abstract summary: Retrosynthesis is a core task in organic synthesis that aims to predict reactants for a given product molecule.<n>We propose RetroReasoner, a retrosynthetic reasoning model that leverages chemists' strategic thinking.<n> Experimental results show that RetroReasoner not only outperforms prior baselines but also generates a broader range of feasible reactant proposals.
• Score: 10.722337545605626
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Retrosynthesis prediction is a core task in organic synthesis that aims to predict reactants for a given product molecule. Traditionally, chemists select a plausible bond disconnection and derive corresponding reactants, which is time-consuming and requires substantial expertise. While recent advancements in molecular large language models (LLMs) have made progress, many methods either predict reactants without strategic reasoning or conduct only a generic product analysis, rather than reason explicitly about bond-disconnection strategies that logically lead to the choice of specific reactants. To overcome these limitations, we propose RetroReasoner, a retrosynthetic reasoning model that leverages chemists' strategic thinking. RetroReasoner is trained using both supervised fine-tuning (SFT) and reinforcement learning (RL). For SFT, we introduce SyntheticRetro, a framework that generates structured disconnection rationales alongside reactant predictions. In the case of RL, we apply a round-trip accuracy as reward, where predicted reactants are passed through a forward synthesis model, and predictions are rewarded when the forward-predicted product matches the original input product. Experimental results show that RetroReasoner not only outperforms prior baselines but also generates a broader range of feasible reactant proposals, particularly in handling more challenging reaction instances.

Related papers

• Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis [3.841858001721215]
  We introduce Top-K prompting as a robust training and inference paradigm to better capture diverse, plausible reaction predictions.<n>We compile CREED-CCV-2+USPTO-XL, an ultra-large-scale dataset of 45.6 million verified reactions to train the C3LM.
  arXiv  Detail & Related papers  (2026-08-19T14:08:05Z)
• Modular Multi-Task Learning for Chemical Reaction Prediction [1.443416244644791]
  Low-Rank Adaptation (LoRA) is a parameter-efficient alternative to full fine-tuning for organic reaction prediction.<n>LoRA achieves accuracy comparable to full fine-tuning while effectively mitigating catastrophic forgetting and better preserving multi-task performance.
  arXiv  Detail & Related papers  (2026-02-11T01:17:06Z)
• Enhancing Chemical Reaction and Retrosynthesis Prediction with Large Language Model and Dual-task Learning [8.402406301818905]
  Large language models (LLMs) have shown potential in many domains.<n>ChemDual is a novel framework for accurate chemical synthesis.<n>ChemDual achieves state-of-the-art performance in both predictions of reaction and retrosynthesis.
  arXiv  Detail & Related papers  (2025-05-05T13:31:36Z)
• Chemist-aligned retrosynthesis by ensembling diverse inductive bias models [5.47805641978534]
  RetroChimera is a frontier retrosynthesis model built upon two newly developed components with complementary inductive biases.<n>We show it outperforms all major models by a large margin, demonstrating robustness outside the training data.<n>We also demonstrate zero-shot transfer to an internal dataset from a major pharmaceutical company.
  arXiv  Detail & Related papers  (2024-12-06T18:55:19Z)
• 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)
• log-RRIM: Yield Prediction via Local-to-global Reaction Representation Learning and Interaction Modeling [6.310759215182946]
  log-RRIM is an innovative graph transformer-based framework designed for predicting chemical reaction yields.<n>A key feature of log-RRIM is its integration of a cross-attention mechanism that focuses on the interplay between reagents and reaction centers.<n>Log-RRIM shows superior performance in our experiments, especially for medium to high-yielding reactions.
  arXiv  Detail & Related papers  (2024-10-20T18:35:56Z)
• BatGPT-Chem: A Foundation Large Model For Retrosynthesis Prediction [65.93303145891628]
  BatGPT-Chem is a large language model with 15 billion parameters, tailored for enhanced retrosynthesis prediction. Our model captures a broad spectrum of chemical knowledge, enabling precise prediction of reaction conditions. This development empowers chemists to adeptly address novel compounds, potentially expediting the innovation cycle in drug manufacturing and materials science.
  arXiv  Detail & Related papers  (2024-08-19T05:17:40Z)
• Retrosynthesis prediction enhanced by in-silico reaction data augmentation [66.5643280109899]
  We present RetroWISE, a framework that employs a base model inferred from real paired data to perform in-silico reaction generation and augmentation. On three benchmark datasets, RetroWISE achieves the best overall performance against state-of-the-art models.
  arXiv  Detail & Related papers  (2024-01-31T07:40:37Z)
• Beyond the Typical: Modeling Rare Plausible Patterns in Chemical Reactions by Leveraging Sequential Mixture-of-Experts [42.9784548283531]
  Generative models like Transformer and VAE have typically been employed to predict the reaction product. We propose organizing the mapping space between reactants and electron redistribution patterns in a divide-and-conquer manner.
  arXiv  Detail & Related papers  (2023-10-07T03:18:26Z)
• Self-Improved Retrosynthetic Planning [66.5397931294144]
  Retrosynthetic planning is a fundamental problem in chemistry for finding a pathway of reactions to synthesize a target molecule. Recent search algorithms have shown promising results for solving this problem by using deep neural networks (DNNs) We propose an end-to-end framework for directly training the DNNs towards generating reaction pathways with the desirable properties.
  arXiv  Detail & Related papers  (2021-06-09T08:03:57Z)
• RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning [107.64562550844146]
  Retrosynthesis is an emerging research area of deep learning. We propose a new approach that reformulating retrosynthesis into a selection problem of reactants from a candidate set of commercially available molecules. For learning the score functions, we also propose a novel contrastive training scheme with hard negative mining.
  arXiv  Detail & Related papers  (2021-05-03T12:47:57Z)
• RetroXpert: Decompose Retrosynthesis Prediction like a Chemist [60.463900712314754]
  We devise a novel template-free algorithm for automatic retrosynthetic expansion. Our method disassembles retrosynthesis into two steps. While outperforming the state-of-the-art baselines, our model also provides chemically reasonable interpretation.
  arXiv  Detail & Related papers  (2020-11-04T04:35:34Z)
• Retrosynthesis Prediction with Conditional Graph Logic Network [118.70437805407728]
  Computer-aided retrosynthesis is finding renewed interest from both chemistry and computer science communities. We propose a new approach to this task using the Conditional Graph Logic Network, a conditional graphical model built upon graph neural networks.
  arXiv  Detail & Related papers  (2020-01-06T05:36:57Z)

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.