# Self-Improved Retrosynthetic Planning

arXiv: https://arxiv.org/abs/2106.04880 · HTML: https://mlsanity.com/paper/2106.04880/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 34 references that are in the map.
- First posted on arXiv 9 Jun 2021.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Thinking Fast and Slow with Deep Learning and Tree Search](https://mlsanity.com/paper/1705.08439/) (2017)
- [Molecular Transformer - A Model for Uncertainty-Calibrated Chemical Reaction Prediction](https://mlsanity.com/paper/1811.02633/) (2018)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [Retrosynthesis Prediction with Conditional Graph Logic Network](https://mlsanity.com/paper/2001.01408/) (2020)
- [Predicting Organic Reaction Outcomes with Weisfeiler-Lehman Network](https://mlsanity.com/paper/1709.04555/) (2017)
- [Retrosynthetic reaction prediction using neural sequence-to-sequence models](https://mlsanity.com/paper/1706.01643/) (2017)
- [A Graph to Graphs Framework for Retrosynthesis Prediction](https://mlsanity.com/paper/2003.12725/) (2020)
- [Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search](https://mlsanity.com/paper/2006.15820/) (2020)
- [RetroXpert: Decompose Retrosynthesis Prediction like a Chemist](https://mlsanity.com/paper/2011.02893/) (2020)
- [Graph Transformation Policy Network for Chemical Reaction Prediction](https://mlsanity.com/paper/1812.09441/) (2018)
- ["Found in Translation": Predicting Outcomes of Complex Organic Chemistry Reactions using Neural Sequence-to-Sequence Models](https://mlsanity.com/paper/1711.04810/) (2017)
- [A Generative Model For Electron Paths](https://mlsanity.com/paper/1805.10970/) (2018)
- [Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees](https://mlsanity.com/paper/1903.00070/) (2019)
- [Learning to Search via Retrospective Imitation](https://mlsanity.com/paper/1804.00846/) (2018)
- [Policy Gradient Search: Online Planning and Expert Iteration without Search Trees](https://mlsanity.com/paper/1904.03646/) (2019)
- [RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design](https://mlsanity.com/paper/2011.13042/) (2020)

## Built on by (most cited first, 23 of 23)

- [Re-evaluating Retrosynthesis Algorithms with Syntheseus](https://mlsanity.com/paper/2310.19796/) (2023)
- [RetroGraph: Retrosynthetic Planning with Graph Search](https://mlsanity.com/paper/2206.11477/) (2022)
- [Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search](https://mlsanity.com/paper/2407.06334/) (2024)
- [Retrosynthetic Planning with Dual Value Networks](https://mlsanity.com/paper/2301.13755/) (2023)
- [Retro-fallback: retrosynthetic planning in an uncertain world](https://mlsanity.com/paper/2310.09270/) (2023)
- [Retrosynthetic Planning with Experience-Guided Monte Carlo Tree Search](https://mlsanity.com/paper/2112.06028/) (2021)
- [FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning](https://mlsanity.com/paper/2209.15315/) (2022)
- [AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search](https://mlsanity.com/paper/2509.20988/) (2025)
- [LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Framework](https://mlsanity.com/paper/2508.11860/) (2025)
- [Mind the Retrosynthesis Gap: Bridging the divide between Single-step and Multi-step Retrosynthesis Prediction](https://mlsanity.com/paper/2212.11809/) (2022)
- [Tango*: Constrained synthesis planning using chemically informed value functions](https://mlsanity.com/paper/2412.03424/) (2024)
- [Preference Optimization for Molecule Synthesis with Conditional Residual Energy-based Models](https://mlsanity.com/paper/2406.02066/) (2024)
- [Procedural Synthesis of Synthesizable Molecules](https://mlsanity.com/paper/2409.05873/) (2024)
- [Recent advances in artificial intelligence for retrosynthesis](https://mlsanity.com/paper/2301.05864/) (2023)
- [Evaluating Molecule Synthesizability via Retrosynthetic Planning and Reaction Prediction](https://mlsanity.com/paper/2411.08306/) (2024)
- [Retro-BLEU: Quantifying Chemical Plausibility of Retrosynthesis Routes through Reaction Template Sequence Analysis](https://mlsanity.com/paper/2311.06304/) (2023)
- [Procrustean Bed for AI-Driven Retrosynthesis: A Unified Framework for Reproducible Evaluation](https://mlsanity.com/paper/2512.07079/) (2025)
- [RetroAgent: Harnessing LLMs to Search Over Structured Memory for Agentic Retrosynthesis Planning](https://mlsanity.com/paper/2607.14512/) (2026)
- [Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs](https://mlsanity.com/paper/2509.10504/) (2025)
- [From Feasible to Practical: Pareto-Optimal Synthesis Planning](https://mlsanity.com/paper/2605.07521/) (2026)
- [URSA: Chemistry-Aware Benchmark for Utilitarian Retrosynthesis Assessment](https://mlsanity.com/paper/2607.04688/) (2026)
- [MMORF: A Multi-agent Framework for Designing Multi-objective Retrosynthesis Planning Systems](https://mlsanity.com/paper/2604.05075/) (2026)
- [Reinforced Reasoning for End-to-End Retrosynthetic Planning](https://mlsanity.com/paper/2603.29723/) (2026)

## Abstract (arXiv)

Retrosynthetic planning is a fundamental problem in chemistry for finding a pathway of reactions to synthesize a target molecule. Recently, search algorithms have shown promising results for solving this problem by using deep neural networks (DNNs) to expand their candidate solutions, i.e., adding new reactions to reaction pathways. However, the existing works on this line are suboptimal; the retrosynthetic planning problem requires the reaction pathways to be (a) represented by real-world reactions and (b) executable using "building block" molecules, yet the DNNs expand reaction pathways without fully incorporating such requirements. Motivated by this, we propose an end-to-end framework for directly training the DNNs towards generating reaction pathways with the desirable properties. Our main idea is based on a self-improving procedure that trains the model to imitate successful trajectories found by itself. We also propose a novel reaction augmentation scheme based on a forward reaction model. Our experiments demonstrate that our scheme significantly improves the success rate of solving the retrosynthetic problem from 86.84% to 96.32% while maintaining the performance of DNN for predicting valid reactions.