@inproceedings{song-etal-2026-aot,
title = "{AOT}*: Efficient Synthesis Planning via {LLM}-Empowered {AND}-{OR} Tree Search",
author = "Song, Xiaozhuang and
Pan, Xuanhao and
Zhao, Xinjian and
Ye, Hangting and
Zhang, Shufei and
Tang, Jian and
Yu, Tianshu",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1734/",
doi = "10.18653/v1/2026.findings-acl.1734",
pages = "34727--34758",
ISBN = "979-8-89176-395-1",
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 LLM-generated 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$\times$ 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."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="song-etal-2026-aot">
<titleInfo>
<title>AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaozhuang</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanhao</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinjian</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hangting</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shufei</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianshu</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<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 LLM-generated 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\times 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.</abstract>
<identifier type="citekey">song-etal-2026-aot</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.1734</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1734/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>34727</start>
<end>34758</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search
%A Song, Xiaozhuang
%A Pan, Xuanhao
%A Zhao, Xinjian
%A Ye, Hangting
%A Zhang, Shufei
%A Tang, Jian
%A Yu, Tianshu
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F song-etal-2026-aot
%X 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* 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 performance advantage becoming more pronounced on complex molecular targets. Our code is available at https://github.com/ShawnKS/AOTstar.
%R 10.18653/v1/2026.findings-acl.1734
%U https://aclanthology.org/2026.findings-acl.1734/
%U https://doi.org/10.18653/v1/2026.findings-acl.1734
%P 34727-34758
Markdown (Informal)
[AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search](https://aclanthology.org/2026.findings-acl.1734/) (Song et al., Findings 2026)
ACL
- Xiaozhuang Song, Xuanhao Pan, Xinjian Zhao, Hangting Ye, Shufei Zhang, Jian Tang, and Tianshu Yu. 2026. AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search. In Findings of the Association for Computational Linguistics: ACL 2026, pages 34727–34758, San Diego, California, United States. Association for Computational Linguistics.