mlsanityData to 7 Oct 2026

Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search

arXiv 2006.15820 ↗First posted 29 Jun 2020cs.LG cs.AI stat.MLcited by 75

Not on the map. Why?

Abstract (arXiv)

Retrosynthetic planning is a critical task in organic chemistry which identifies a series of reactions that can lead to the synthesis of a target product. The vast number of possible chemical transformations makes the size of the search space very big, and retrosynthetic planning is challenging even for experienced chemists. However, existing methods either require expensive return estimation by rollout with high variance, or optimize for search speed rather than the quality. In this paper, we propose Retro*, a neural-based A*-like algorithm that finds high-quality synthetic routes efficiently. It maintains the search as an AND-OR tree, and learns a neural search bias with off-policy data. Then guided by this neural network, it performs best-first search efficiently during new planning episodes. Experiments on benchmark USPTO datasets show that, our proposed method outperforms existing state-of-the-art with respect to both the success rate and solution quality, while being more efficient at the same time.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 9; 2023: 12; 2024: 11; 2025: 21; 2026: 14.

75 papers.

Sort:

By area:

  1. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  2. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  3. 2024Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planningcited by 29
  4. 2025KL-Regularized Reinforcement Learning is Designed to Mode Collapsecited by 29
  5. 2022Data-Efficient Graph Grammar Learning for Molecular Generationcited by 26
  6. 2023Re-evaluating Retrosynthesis Algorithms with Syntheseuscited by 26
  7. 2024Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Searchcited by 24
  8. 2025LIDDIA: Language-based Intelligent Drug Discovery Agentcited by 24
  9. 2021Self-Improved Retrosynthetic Planningcited by 23
  10. 2022RetroGraph: Retrosynthetic Planning with Graph Searchcited by 23
  11. 2023Retrosynthetic Planning with Dual Value Networkscited by 20
  12. 2025Chemical reasoning in LLMs unlocks strategy-aware synthesis planning and reaction mechanism elucidationcited by 17
38 more
  1. 2023Retro-fallback: retrosynthetic planning in an uncertain worldcited by 16
  2. 2023Models Matter: The Impact of Single-Step Retrosynthesis on Synthesis Planningcited by 15
  3. 2021Retrosynthetic Planning with Experience-Guided Monte Carlo Tree Searchcited by 14
  4. 2022FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planningcited by 14
  5. 2021Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Predictioncited by 13
  6. 2025LLM-Augmented Chemical Synthesis and Design Decision Programscited by 13
  7. 2025AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Searchcited by 13
  8. 2024DirectMultiStep: Direct Route Generation for Multistep Retrosynthesiscited by 11
  9. 2023Deep Learning Methods for Small Molecule Drug Discovery: A Surveycited by 10
  10. 2024RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNetscited by 10
  11. 2025Synthelite: Chemist-aligned and feasibility-aware synthesis planning with LLMscited by 10
  12. 2025LARC: Towards Human-level Constrained Retrosynthesis Planning through an Agentic Frameworkcited by 9
  13. 2022Learning Graph Search Heuristicscited by 7
  14. 2022Mind the Retrosynthesis Gap: Bridging the divide between Single-step and Multi-step Retrosynthesis Predictioncited by 7
  15. 2024Representing Molecules as Random Walks Over Interpretable Grammarscited by 7
  16. 2024Tango*: Constrained synthesis planning using chemically informed value functionscited by 7
  17. 2021RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learningcited by 6
  18. 2021A generative model for molecule generation based on chemical reaction treescited by 6
  19. 2022Sample Complexity of Learning Heuristic Functions for Greedy-Best-First and A* Searchcited by 6
  20. 2024Procedural Synthesis of Synthesizable Moleculescited by 6
  21. 2025TempRe: Template generation for single and direct multi-step retrosynthesiscited by 6
  22. 2023Recent advances in artificial intelligence for retrosynthesiscited by 5
  23. 2023RCsearcher: Reaction Center Identification in Retrosynthesis via Deep Q-Learningcited by 5
  24. 2024Evaluating Molecule Synthesizability via Retrosynthetic Planning and Reaction Predictioncited by 5
  25. 2024Chemist-aligned retrosynthesis by ensembling diverse inductive bias modelscited by 5
  26. 2021Embeddings and labeling schemes for A*cited by 4
  27. 2022mathsfG2Retro as a Two-Step Graph Generative Models for Retrosynthesis Predictioncited by 4
  28. 2023Retro-BLEU: Quantifying Chemical Plausibility of Retrosynthesis Routes through Reaction Template Sequence Analysiscited by 4
  29. 2024Towards Learning Foundation Models for Heuristic Functions to Solve Pathfinding Problemscited by 4
  30. 2025Procrustean Bed for AI-Driven Retrosynthesis: A Unified Framework for Reproducible Evaluationcited by 4
  31. 2023RLSynC: Offline-Online Reinforcement Learning for Synthon Completioncited by 3
  32. 2025Survey on Recent Progress of AI for Chemistry: Methods, Applications, and Opportunitiescited by 3
  33. 2025Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesiscited by 3
  34. 2025Constrained Adaptive Rejection Samplingcited by 3
  35. 2025Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorerscited by 3
  36. 2026Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matchingcited by 3
  37. 2021A* Search Without Expansions: Learning Heuristic Functions with Deep Q-Networkscited by 2
  38. 2023Evolutionary Retrosynthetic Route Planningcited by 2

50 most cited of 75 All 75 (JSON)