# Retrosynthetic Planning with Dual Value Networks

arXiv: https://arxiv.org/abs/2301.13755 · HTML: https://mlsanity.com/paper/2301.13755/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 31 Jan 2023.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (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)
- [Retrosynthetic reaction prediction using neural sequence-to-sequence models](https://mlsanity.com/paper/1706.01643/) (2017)
- [Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search](https://mlsanity.com/paper/2006.15820/) (2020)
- [RetroGraph: Retrosynthetic Planning with Graph Search](https://mlsanity.com/paper/2206.11477/) (2022)
- [Self-Improved Retrosynthetic Planning](https://mlsanity.com/paper/2106.04880/) (2021)
- [Mind the Retrosynthesis Gap: Bridging the divide between Single-step and Multi-step Retrosynthesis Prediction](https://mlsanity.com/paper/2212.11809/) (2022)
- [Towards "AlphaChem": Chemical Synthesis Planning with Tree Search and Deep Neural Network Policies](https://mlsanity.com/paper/1702.00020/) (2017)

## Built on by (most cited first, 21 of 21)

- [Re-evaluating Retrosynthesis Algorithms with Syntheseus](https://mlsanity.com/paper/2310.19796/) (2023)
- [Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search](https://mlsanity.com/paper/2407.06334/) (2024)
- [Retro-fallback: retrosynthetic planning in an uncertain world](https://mlsanity.com/paper/2310.09270/) (2023)
- [Models Matter: The Impact of Single-Step Retrosynthesis on Synthesis Planning](https://mlsanity.com/paper/2308.05522/) (2023)
- [LLM-Augmented Chemical Synthesis and Design Decision Programs](https://mlsanity.com/paper/2505.07027/) (2025)
- [AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search](https://mlsanity.com/paper/2509.20988/) (2025)
- [RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNets](https://mlsanity.com/paper/2406.18739/) (2024)
- [Tango*: Constrained synthesis planning using chemically informed value functions](https://mlsanity.com/paper/2412.03424/) (2024)
- [Chemist-aligned retrosynthesis by ensembling diverse inductive bias models](https://mlsanity.com/paper/2412.05269/) (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)
- [Evaluating Molecule Synthesizability via Retrosynthetic Planning and Reaction Prediction](https://mlsanity.com/paper/2411.08306/) (2024)
- [Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching](https://mlsanity.com/paper/2602.13136/) (2026)
- [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)
- [Project Ariadne: Prompt-Conditioned Route Generation for Synthesis Planning](https://mlsanity.com/paper/2606.24184/) (2026)
- [Reinforced Reasoning for End-to-End Retrosynthetic Planning](https://mlsanity.com/paper/2603.29723/) (2026)
- [Margin-calibrated Classifier Guidance for Property-driven Synthesis Planning](https://mlsanity.com/paper/2605.13101/) (2026)
- [Strategy-first synthesis planning for complex natural products](https://mlsanity.com/paper/2608.07454/) (2026)
- [RetroPlanner: Multi-Route Expansion and Multi-Objective Reasoning for LLM-Based Retrosynthesis Planning](https://mlsanity.com/paper/2610.16391/) (2026)

## Abstract (arXiv)

Retrosynthesis, which aims to find a route to synthesize a target molecule from commercially available starting materials, is a critical task in drug discovery and materials design. Recently, the combination of ML-based single-step reaction predictors with multi-step planners has led to promising results. However, the single-step predictors are mostly trained offline to optimize the single-step accuracy, without considering complete routes. Here, we leverage reinforcement learning (RL) to improve the single-step predictor, by using a tree-shaped MDP to optimize complete routes. Specifically, we propose a novel online training algorithm, called Planning with Dual Value Networks (PDVN), which alternates between the planning phase and updating phase. In PDVN, we construct two separate value networks to predict the synthesizability and cost of molecules, respectively. To maintain the single-step accuracy, we design a two-branch network structure for the single-step predictor. On the widely-used USPTO dataset, our PDVN algorithm improves the search success rate of existing multi-step planners (e.g., increasing the success rate from 85.79% to 98.95% for Retro*, and reducing the number of model calls by half while solving 99.47% molecules for RetroGraph). Additionally, PDVN helps find shorter synthesis routes (e.g., reducing the average route length from 5.76 to 4.83 for Retro*, and from 5.63 to 4.78 for RetroGraph). Our code is available at urlhttps://github.com/DiXue98/PDVN.