Saved in:
Bibliographic Details
Main Authors: Song, Xiaozhuang, Pan, Xuanhao, Zhao, Xinjian, Ye, Hangting, Zhang, Shufei, Tang, Jian, Yu, Tianshu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.20988
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908560414212096
author Song, Xiaozhuang
Pan, Xuanhao
Zhao, Xinjian
Ye, Hangting
Zhang, Shufei
Tang, Jian
Yu, Tianshu
author_facet Song, Xiaozhuang
Pan, Xuanhao
Zhao, Xinjian
Ye, Hangting
Zhang, Shufei
Tang, Jian
Yu, Tianshu
contents 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 LLM-generated chemical synthesis pathways with systematic AND-OR tree search. To this end, AOT* atomically 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$\times$ fewer iterations than existing LLM-based approaches, with the efficiency advantage becoming more pronounced on complex molecular targets.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20988
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search
Song, Xiaozhuang
Pan, Xuanhao
Zhao, Xinjian
Ye, Hangting
Zhang, Shufei
Tang, Jian
Yu, Tianshu
Artificial Intelligence
Quantitative Methods
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 LLM-generated chemical synthesis pathways with systematic AND-OR tree search. To this end, AOT* atomically 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$\times$ fewer iterations than existing LLM-based approaches, with the efficiency advantage becoming more pronounced on complex molecular targets.
title AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search
topic Artificial Intelligence
Quantitative Methods
url https://arxiv.org/abs/2509.20988