Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |