ACL Findings2026
AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search
Xiaozhuang Song, Xuanhao Pan, Xinjian Zhao, Hangting Ye, Shufei Zhang, Jian Tang, Tianshu Yu
Abstract
Retrosynthesis planning enables the discovery of viable synthetic routes for target molecules, playing a crucial role in domains like drug discovery and materials design. Multi-step retrosynthetic planning remains computationally challenging due to exponential search spaces and inference costs. While Large Language Models (LLMs) demonstrate chemical reasoning capabilities, their application to synthesis planning faces constraints on efficiency and cost. To address these challenges, we introduce AOT*, a framework that transforms retrosynthetic planning by integrating LLMgenerated chemical synthesis pathways with systematic AND-OR tree search. To this end, AOT* maps the generated complete synthesis routes onto AND-OR tree components, with a mathematically sound design of reward assignment strategy and retrieval-based context engineering, thus enabling LLMs to efficiently navigate in the chemical space. Experimental evaluation on multiple synthesis benchmarks demonstrates that AOT* achieves SOTA performance with significantly improved search efficiency. AOT* exhibits competitive solve rates using 3-5× fewer iterations than existing LLM-based approaches, with the performance advantage becoming more pronounced on complex molecular targets. Our code is available at https://github.com/ShawnKS/AOTstar.
Connor W Coley, William H Green, and Klavs F Jensen.
- Rdchiral: An rdkit wrapper for handling stere- ochemistry in retrosynthetic template extraction and application.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers2
- RetrOrchestrator: A Multi-Step Retrosynthesis Agent Dynamically Orchestrating Single-Step Transition ModelsLiao Chang, Luotian Yuan, Yiping Ke, Ying WeiICML 2026
- Towards Diverse Scientific Hypothesis Search with Large Language ModelsHaorui Wang, Parshin Shojaee, Kazem Meidani, Kunyang Sun et al.ICML 2026
Builds on14
- Retrieval-Augmented Generation for Knowledge-Intensive NLP TasksPatrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni et al.NeurIPS 2020 · 19,162 citations
- A Graph to Graphs Framework for Retrosynthesis PredictionChence Shi, Minkai Xu, Hongyu Guo, Ming Zhang et al.ICML 2020 · 176 citations
- Retro*: Learning Retrosynthetic Planning with Neural Guided A* SearchBinghong Chen, Chengtao Li, Hanjun Dai, Le SongICML 2020 · 151 citations
- Learning Graph Models for Retrosynthesis PredictionVignesh Ram Somnath, Charlotte Bunne, Connor W. Coley, Andreas Krause et al.NeurIPS 2021 · 137 citations
- Translation between Molecules and Natural LanguageCarl Edwards, Tuan Manh Lai, Kevin Ros, Garrett Honke et al.EMNLP 2022 · 112 citations
Related papers
- LLM-Augmented Chemical Synthesis and Design Decision ProgramsHaorui Wang, Jeff Guo, Lingkai Kong, Rampi Ramprasad et al.ICML 2025
- Retro-R1: LLM-based Agentic RetrosynthesisWei Liu, Jiangtao Feng, Hongli Yu, Yuxuan Song et al.NeurIPS 2025 · 8 citations
- RetroInText: A Multimodal Large Language Model Enhanced Framework for Retrosynthetic Planning via In-Context Representation LearningChenglong Kang, Xiaoyi Liu, Fei GuoICLR 2025
- LLMs Can Reason Faster Only If We Let ThemBilgehan Sel, Lifu Huang, Naren Ramakrishnan, Ruoxi Jia et al.ICML 2025
- LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path PlanningSilin Meng, Yiwei Wang, Cheng-Fu Yang, Nanyun Peng et al.EMNLP Findings 2024 · 37 citations
