# RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis Prediction

arXiv: https://arxiv.org/abs/2603.12666 · HTML: https://mlsanity.com/paper/2603.12666/

## 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 22 of its 56 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [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)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models](https://mlsanity.com/paper/2306.08018/) (2023)
- [LlaSMol: Advancing Large Language Models for Chemistry with a Large-Scale, Comprehensive, High-Quality Instruction Tuning Dataset](https://mlsanity.com/paper/2402.09391/) (2024)
- [Training a Scientific Reasoning Model for Chemistry](https://mlsanity.com/paper/2506.17238/) (2025)
- [BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning](https://mlsanity.com/paper/2402.17810/) (2024)
- [ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge](https://mlsanity.com/paper/2507.21990/) (2025)
- [Chem-R: Learning to Reason as a Chemist](https://mlsanity.com/paper/2510.16880/) (2025)
- [PRESTO: Progressive Pretraining Enhances Synthetic Chemistry Outcomes](https://mlsanity.com/paper/2406.13193/) (2024)
- [Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search](https://mlsanity.com/paper/1810.11755/) (2018)
- [Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction](https://mlsanity.com/paper/2104.03279/) (2021)
- [AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search](https://mlsanity.com/paper/2509.20988/) (2025)
- [Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization](https://mlsanity.com/paper/2502.02810/) (2025)
- [TempRe: Template generation for single and direct multi-step retrosynthesis](https://mlsanity.com/paper/2507.21762/) (2025)
- [RetroDFM-R: Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning](https://mlsanity.com/paper/2507.17448/) (2025)
- [Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis](https://mlsanity.com/paper/2508.10967/) (2025)

## Abstract (arXiv)

Retrosynthesis prediction aims to identify reactants that can synthesize a given product molecule. Although molecular large language models (LLMs) have recently shown promising results, most existing methods either generate reactants directly or provide only generic product-level analysis, without explicitly reasoning about bond-disconnection strategies that justify specific reactant choices. This paper proposes RetroReasoner, a retrosynthetic reasoning model that captures chemists' strategic disconnection-based thinking. RetroReasoner is trained with supervised fine-tuning and reinforcement learning. For supervised fine-tuning, SyntheticRetro generates structured disconnection rationales paired with reactant predictions. For reinforcement learning, a round-trip reward evaluates predicted reactants by passing them through a forward synthesis model and rewarding predictions that reconstruct the original product. RetroReasoner can also be applied to multi-step retrosynthetic planning by incorporating it into a parallelized Monte Carlo tree search framework, reducing search time while increasing the number and diversity of valid synthetic pathways. Experimental results show that RetroReasoner outperforms prior baselines, including not only molecular LLMs but also retrosynthesis-specific expert models, and generates a broader range of feasible reactant proposals, especially for challenging reaction instances. The code is available at https://github.com/KU-AGI/RetroReasoner.