Elamur Research⌕
☰
home / papers / 2026 / AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search

AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search

Paper · 2026 · Xiaozhuang Song, Xuanhao Pan, Xinjian Zhao et al.

Summary

AOT* is a method for multi-step retrosynthesis planning, which means finding a chain of reactions that breaks a target molecule down into purchasable building blocks. Existing neural and LLM-based planners can be costly. LLM-Syn-Planner, for example, refines whole routes through evolutionary search and needs many expensive LLM calls. AOT* takes a different approach. It asks an LLM to propose complete multi-step routes for unsolved molecules and grafts each valid route onto a classical AND-OR tree, where OR nodes are molecules and AND nodes are reactions. Canonical SMILES ensure each molecule appears only once in the tree, so intermediates found earlier can be reused. Route steps that target molecules already solved are dropped. Leaf reactions to expand next are chosen with a UCB rule. Prompts include a few similar known routes, retrieved by Tanimoto similarity on Morgan fingerprints, and reaction templates filter out invalid chemistry. Across benchmarks, AOT* reaches competitive or better solve rates in 3–5× fewer iterations, with larger gains on hard targets. This makes LLM-driven synthesis planning more practical when compute or API budgets are limited.

Key points

  • On Pistachio Hard with DeepSeek-V3, AOT* solves 67% of targets at 20 iterations and 86% at 100. Under the same budgets, LLM-Syn-Planner reaches 13% and 74%. GPT-4o shows a similar pattern: 64%/85% versus 9%/72%.
  • Retrieval matters but saturates quickly. Without retrieved examples the solve rate is 60%, and with 3 examples it is 86%. Going up to 20 examples adds only about 2 points while increasing tokens by 177% (1,478 → 4,091).
  • The gains hold across five LLMs: GPT-4o-mini, DeepSeek-V3, GPT-4o, Claude-4-Sonnet and Gemini-2.5 Pro. DeepSeek-V3 gives the best balance of cost and performance.
  • The method is not very sensitive to hyperparameters. Solve rates stay between 77% and 86%, with the best setting at exploration constant c = 0.5 and temperature 0.7.
  • The authors list several limitations. Results depend on the LLM's chemical knowledge and on the quality of retrieved examples, so performance may drop for complex natural products and novel chemical spaces. The method has no multi-objective search or uncertainty estimates yet. Code is available at github.com/ShawnKS/AOTstar.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🔬Shanghai Artificial Intelligence LaboratoryShanghai · China117 works · 11,281 citations🔬Mila - Quebec Artificial Intelligence InstituteMontreal · Canada54 works · 13,565 citations🎓Chinese University of Hong Kong, ShenzhenShenzhen · China47 works · 2,596 citations🎓Jilin UniversityChangchun · China25 works · 5,252 citations🎓HEC MontréalMontreal · Canada5 works · 9,748 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksComputational Theory and Mathematics · 252 worksMaterials Science · 26 worksMaterials Chemistry · 26 works

🧭 Topics 1Research subjects and languages the work is about.Language models & pretraining · 3,320 works

Cite

Cite as 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. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.findings-acl.1734

@inproceedings{song2026aot,
  title = {{AOT*: Efficient Synthesis Planning via LLM-Empowered AND-OR Tree Search}},
  author = {Xiaozhuang Song, Xuanhao Pan, Xinjian Zhao, Hangting Ye, Shufei Zhang, Jian Tang and Tianshu Yu},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.1734},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.1734}
}

References

79 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Daniil A Boiko, Robert MacKnight, Ben Kline, and Gabe Gomes. 2023. Autonomous chemical research with large language models. Nature, 624(7992):570– 578.
  2. Andres M Bran, Theo A Neukomm, Daniel P Armstrong, Zlatko Jončev, and Philippe Schwaller. 2025. Chemical reasoning in llms unlocks steerable synthesis planning and reaction mechanism elucidation. arXiv preprint arXiv:2503.08537. find
  3. Sébastien Bubeck, Nicolo Cesa-Bianchi, and 1 others. 2012. Regret analysis of stochastic and nonstochastic multi-armed bandit problems. Foundations and Trends® in Machine Learning, 5(1):1–122. find
  4. Binghong Chen, Chengtao Li, Hanjun Dai, and Le Song. 2020. Retro*: learning retrosynthetic planning with neural guided a* search. In International conference on machine learning, pages 1608–1616. PMLR. find
  5. Shuan Chen and Yousung Jung. 2021. Deep retrosynthetic reaction prediction using local reactivity and global attention. JACS Au, 1(10):1612–1620. find
  6. Clara D Christ, Matthias Zentgraf, and Jan M Kriegl. 2012. Mining electronic laboratory notebooks: analysis, retrosynthesis, and reaction based enumeration. Journal of chemical information and modeling, 52(7):1745–1756. find
  7. Mikhail Andronov, Natalia Andronova, Michael Wand, Jürgen Schmidhuber, and Djork-Arné Clevert. 2025. Fast and scalable retrosynthetic planning with a transformer neural network and speculative beam search. arXiv preprint arXiv:2508.01459. — [arXiv:2508.01459](https://arxiv.org/abs/2508.01459) find
  8. Connor W Coley, William H Green, and Klavs F Jensen. 2019. Rdchiral: An rdkit wrapper for handling stereochemistry in retrosynthetic template extraction and application. Journal of chemical information and modeling, 59(6):2529–2537. find
  9. Anthropic. 2025. Claude Opus 4 & Claude Sonnet 4 -System Card. find
  10. Connor W Coley, Luke Rogers, William H Green, and Klavs F Jensen. 2017. Computer-assisted retrosynthesis based on molecular similarity. ACS central science, 3(12):1237–1245. find
  11. Peter Auer, Nicolo Cesa-Bianchi, and Paul Fischer. 2002. Finite-time analysis of the multiarmed bandit problem. Machine learning, 47(2):235–256. find
  12. Dávid Bajusz, Anita Rácz, and Károly Héberger. 2015. Why is tanimoto index an appropriate choice for fingerprint-based similarity calculations? Journal of cheminformatics, 7(1):20. find
  13. Hans-Georg Beyer and Hans-Paul Schwefel. 2002. Evolution strategies–a comprehensive introduction. Natural computing, 1(1):3–52. find
  14. Krisztina Boda, Thomas Seidel, and Johann Gasteiger. 2007. Structure and reaction based evaluation of synthetic accessibility. Journal of computer-aided molecular design, 21(6):311–325. find
  15. Anders Bøgevig, Hans-Jurgen Federsel, Fernando Huerta, Michael G Hutchings, Hans Kraut, Thomas Langer, Peter Low, Christoph Oppawsky, Tobias Rein, and Heinz Saller. 2015. Route design in the 21st century: the ic synth software tool as an idea generator for synthesis prediction. Organic Process Resea… find
  16. Connor W Coley, Luke Rogers, William H Green, and Klavs F Jensen. 2018. Scscore: synthetic complexity learned from a reaction corpus. Journal of chemical information and modeling, 58(2):252–261. find
  17. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, and 1 others. 2025. Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arX…
  18. Elias James Corey and W Todd Wipke. 1969. Computer-assisted design of complex organic syntheses: Pathways for molecular synthesis can be devised with a computer and equipment for graphical communication. Science, 166(3902):178–192. find
  19. Hanjun Dai, Chengtao Li, Connor Coley, Bo Dai, and Le Song. 2019. Retrosynthesis prediction with conditional graph logic network. Advances in Neural Information Processing Systems, 32. find
  20. Yafeng Deng, Xinda Zhao, Hanyu Sun, Yu Chen, Xiaorui Wang, Xi Xue, Liangning Li, Jianfei Song, Chang-Yu Hsieh, Tingjun Hou, and 1 others. 2025. Rsgpt: a generative transformer model for retrosynthesis planning pre-trained on ten billion datapoints. Nature Communications, 16(1):7012. find
  21. Jingxin Dong, Mingyi Zhao, Yuansheng Liu, Yansen Su, and Xiangxiang Zeng. 2022. Deep learning in retrosynthesis planning: datasets, models and tools. Briefings in Bioinformatics, 23(1). find
  22. Carl Edwards, Tuan Lai, Kevin Ros, Garrett Honke, Kyunghyun Cho, and Heng Ji. 2022. Translation between molecules and natural language. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 375–413.
  23. Walter Fontana. 1990. Algorithmic chemistry. Technical report, Los Alamos National Lab., NM (USA). find
  24. Samuel Genheden and Esben Bjerrum. 2022. Paroutes: towards a framework for benchmarking retrosynthesis route predictions. Digital Discovery, 1(4):527– 539. find
  25. Samuel Genheden, Amol Thakkar, Veronika Chadimová, Jean-Louis Reymond, Ola Engkvist, and Esben Bjerrum. 2020. Aizynthfinder: a fast, robust and flexible open-source software for retrosynthetic planning. Journal of cheminformatics, 12(1):70. find
  26. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783.
  27. Bartosz A Grzybowski, Kyle JM Bishop, Bartlomiej Kowalczyk, and Christopher E Wilmer. 2009. The’wired’universe of organic chemistry. Nature Chemistry, 1(1):31–36. find
  28. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, and 1 others. 2025. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. arXiv preprint arXiv:2501.12948.
  29. Taicheng Guo, Bozhao Nan, Zhenwen Liang, Zhichun Guo, Nitesh Chawla, Olaf Wiest, Xiangliang Zhang, and 1 others. 2023. What can large language models do in chemistry? a comprehensive benchmark on eight tasks. Advances in Neural Information Processing Systems, 36:59662–59688. find
  30. Kevin Maik Jablonka, Philippe Schwaller, Andres Ortega-Guerrero, and Berend Smit. 2024. Leveraging large language models for predictive chemistry. Nature Machine Intelligence, 6(2):161–169. find
  31. Zlatko Jončev, Jeff Guo, Philippe Schwaller, and 1 others. 2025. Tango*: Constrained synthesis planning using chemically informed value functions. Digital Discovery. find
  32. Subbarao Kambhampati, Karthik Valmeekam, Lin Guan, Mudit Verma, Kaya Stechly, Siddhant Bhambri, Lucas Saldyt, and Anil Murthy. 2024. Llms can’t plan, but can help planning in llm-modulo frameworks. arXiv preprint arXiv:2402.01817. find
  33. Junsu Kim, Sungsoo Ahn, Hankook Lee, and Jinwoo Shin. 2021. Self-improved retrosynthetic planning. In International Conference on Machine Learning, pages 5486–5495. PMLR. find
  34. Akihiro Kishimoto, Beat Buesser, Bei Chen, and Adi Botea. 2019. Depth-first proof-number search with heuristic edge cost and application to chemical synthesis planning. Advances in Neural Information Processing Systems, 32. find
  35. James Law, Zsolt Zsoldos, Aniko Simon, Darryl Reid, Yang Liu, Sing Yoong Khew, A Peter Johnson, Sarah Major, Robert A Wade, and Howard Y Ando. 2009. Route designer: a retrosynthetic analysis tool utilizing automated retrosynthetic rule generation. Journal of chemical information and modeling, 49(3):… find
  36. Xiao Qing Lewell, Duncan B Judd, Stephen P Watson, and Michael M Hann. 1998. Recap retrosynthetic combinatorial analysis procedure: a powerful new technique for identifying privileged molecular fragments with useful applications in combinatorial chemistry. Journal of chemical information and compute… find
  37. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, and 1 others. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33:9459–…
  38. Min Htoo Lin, Zhengkai Tu, and Connor W Coley. 2022. Improving the performance of models for one-step retrosynthesis through re-ranking. Journal of cheminformatics, 14(1):15. find
  39. Siqi Hong, Hankz Hankui Zhuo, Kebing Jin, Guang Shao, and Zhanwen Zhou. 2023. Retrosynthetic planning with experience-guided monte carlo tree search. Communications Chemistry, 6(1):120. find
  40. Xuan Lin, Qingrui Liu, Hongxin Xiang, Daojian Zeng, and Xiangxiang Zeng. 2025. Enhancing chemical reaction and retrosynthesis prediction with large language model and dual-task learning. arXiv preprint arXiv:2505.02639. — [arXiv:2505.02639](https://arxiv.org/abs/2505.02639) find
  41. Aaron Hurst, Adam Lerer, Adam P Goucher, Adam Perelman, Aditya Ramesh, Aidan Clark, AJ Ostrow, Akila Welihinda, Alan Hayes, Alec Radford, and 1 others. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276.
  42. Aixin Liu, Bei Feng, Bing Xue, Bingxuan Wang, Bochao Wu, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chenyu Zhang, Chong Ruan, and 1 others. 2024. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437. find
  43. Bowen Liu, Bharath Ramsundar, Prasad Kawthekar, Jade Shi, Joseph Gomes, Quang Luu Nguyen, Stephen Ho, Jack Sloane, Paul Wender, and Vijay Pande. 2017. Retrosynthetic reaction prediction using neural sequence-to-sequence models. ACS central science, 3(10):1103–1113. find
  44. Gang Liu, Michael Sun, Wojciech Matusik, Meng Jiang, and Jie Chen. 2025. Multimodal large language models for inverse molecular design with retrosynthetic planning. In International Conference on Learning Representations. find
  45. Guoqing Liu, Di Xue, Shufang Xie, Yingce Xia, Austin Tripp, Krzysztof Maziarz, Marwin Segler, Tao Qin, Zongzhang Zhang, and Tie-Yan Liu. 2023. Retrosynthetic planning with dual value networks. In International conference on machine learning, pages 22266– 22276. PMLR. find
  46. Andres M. Bran, Sam Cox, Oliver Schilter, Carlo Baldassari, Andrew D White, and Philippe Schwaller. 2024. Augmenting large language models with chemistry tools. Nature Machine Intelligence, 6(5):525– 535. find
  47. Krzysztof Maziarz, Austin Tripp, Guoqing Liu, Megan Stanley, Shufang Xie, Piotr Gaiński, Philipp Seidl, and Marwin HS Segler. 2025. Re-evaluating retrosynthesis algorithms with syntheseus. Faraday Discussions, 256:568–586. find
  48. Adrian Mirza, Nawaf Alampara, Sreekanth Kunchapu, Martiño Ríos-García, Benedict Emoekabu, Aswanth Krishnan, Tanya Gupta, Mara Schilling-Wilhelmi, Macjonathan Okereke, Anagha Aneesh, and 1 others. 2025. A framework for evaluating the chemical knowledge and reasoning abilities of large language models… find
  49. KC Nicolaou and Jason S Chen. 2009. The art of total synthesis through cascade reactions. Chemical Society Reviews, 38(11):2993–3009. find
  50. Noel M O’Boyle. 2012. Towards a universal smiles representation-a standard method to generate canonical smiles based on the inchi. Journal of cheminformatics, 4(1):22. find
  51. Lakshidaa Saigiridharan, Alan Kai Hassen, Helen Lai, Paula Torren-Peraire, Ola Engkvist, and Samuel Genheden. 2024. Aizynthfinder 4.0: developments based on learnings from 3 years of industrial application. Journal of cheminformatics, 16(1):57. find
  52. Shreyas Vinaya Sathyanarayana, Sharanabasava D Hiremath, Rahil Shah, Rishikesh Panda, Rahul Jana, Riya Singh, Rida Irfan, Ashwin Murali, and Bharath Ramsundar. 2025. Deepretro: Retrosynthetic pathway discovery using iterative llm reasoning. arXiv preprint arXiv:2507.07060. — [arXiv:2507.07060](https://arxiv.org/abs/2507.07060) find
  53. John S Schreck, Connor W Coley, and Kyle JM Bishop. 2019. Learning retrosynthetic planning through simulated experience. ACS central science, 5(6):970–981. find
  54. Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A Hunter, Costas Bekas, and Alpha A Lee. 2019. Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS central science, 5(9):1572–1583. find
  55. Philippe Schwaller, Riccardo Petraglia, Valerio Zullo, Vishnu H Nair, Rico Andreas Haeuselmann, Riccardo Pisoni, Costas Bekas, Anna Iuliano, and Teodoro Laino. 2020. Predicting retrosynthetic pathways using transformer-based models and a hyper-graph exploration strategy. Chemical science, 11(12):331… find
  56. Marwin HS Segler, Mike Preuss, and Mark P Waller. 2018. Planning chemical syntheses with deep neural networks and symbolic ai. Nature, 555(7698):604– 610. find
  57. Marwin HS Segler and Mark P Waller. 2017. Neural-symbolic machine learning for retrosynthesis and reaction prediction. Chemistry–A European Journal, 23(25):5966–5971. find
  58. Chence Shi, Minkai Xu, Hongyu Guo, Ming Zhang, and Jian Tang. 2020. A graph to graphs framework for retrosynthesis prediction. In International conference on machine learning, pages 8818–8827. PMLR. find
  59. Vignesh Ram Somnath, Charlotte Bunne, Connor Coley, Andreas Krause, and Regina Barzilay. 2021. Learning graph models for retrosynthesis prediction. Advances in Neural Information Processing Systems, 34:9405–9415. find
  60. Xiaozhuang Song, Shufei Zhang, and Tianshu Yu. 2025. Rekg-mcts: Reinforcing llm reasoning on knowledge graphs via training-free monte carlo tree search. In Findings of the Association for Computational Linguistics: ACL 2025, pages 9288–9306. find
  61. Haoran Sun, Katayoon Goshvadi, Azade Nova, Dale Schuurmans, and Hanjun Dai. 2023. Revisiting sampling for combinatorial optimization. In International Conference on Machine Learning, pages 32859–32874. PMLR. find
  62. Qwen Team. 2025. Qwen3-max: Just scale it. find
  63. Amol Thakkar, Veronika Chadimová, Esben Jannik Bjerrum, Ola Engkvist, and Jean-Louis Reymond. 2021. Retrosynthetic accessibility score (rascore)– rapid machine learned synthesizability classification from ai driven retrosynthetic planning. Chemical science, 12(9):3339–3349. find
  64. Austin Tripp, Krzysztof Maziarz, Sarah Lewis, Marwin Segler, and José Miguel Hernández-Lobato. 2023. Retro-fallback: retrosynthetic planning in an uncertain world. arXiv preprint arXiv:2310.09270. — [arXiv:2310.09270](https://arxiv.org/abs/2310.09270) find
  65. Zhengkai Tu, Sourabh J Choure, Mun Hong Fong, Jihye Roh, Itai Levin, Kevin Yu, Joonyoung F Joung, Nathan Morgan, Shih-Cheng Li, Xiaoqi Sun, and 1 others. 2025. Askcos: Open-source, data-driven synthesis planning. Accounts of Chemical Research, 58(11):1764–1775. find
  66. Haorui Wang, Jeff Guo, Lingkai Kong, Rampi Ramprasad, Philippe Schwaller, Yuanqi Du, and Chao Zhang. 2025. Llm-augmented chemical synthesis and design decision programs. arXiv preprint arXiv:2505.07027. — [arXiv:2505.07027](https://arxiv.org/abs/2505.07027) find
  67. Jiapu Wang, Sun Kai, Linhao Luo, Wei Wei, Yongli Hu, Alan Wee-Chung Liew, Shirui Pan, and Baocai Yin. 2024. Large language models-guided dynamic adaptation for temporal knowledge graph reasoning. Advances in Neural Information Processing Systems, 37:8384–8410. find
  68. Yu Wang, Chao Pang, Yuzhe Wang, Junru Jin, Jingjie Zhang, Xiangxiang Zeng, Ran Su, Quan Zou, and Leyi Wei. 2023. Retrosynthesis prediction with an interpretable deep-learning framework based on molecular assembly tasks. Nature Communications, 14(1):6155. find
  69. David Weininger. 1988. Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. Journal of chemical information and computer sciences, 28(1):31–36. find
  70. Andrew D White, Glen M Hocky, Heta A Gandhi, Mehrad Ansari, Sam Cox, Geemi P Wellawatte, Subarna Sasmal, Ziyue Yang, Kangxin Liu, Yuvraj Singh, and 1 others. 2023. Assessment of chemistry knowledge in large language models that generate code. Digital Discovery, 2(2):368–376. xAI. 2025. Grok 4. https… find
  71. Yifei Yang, Runhan Shi, Zuchao Li, Shu Jiang, Bao-Liang Lu, Yang Yang, and Hai Zhao. 2024. Batgpt-chem: A foundation large model for retrosynthesis prediction. arXiv preprint arXiv:2408.10285. — [arXiv:2408.10285](https://arxiv.org/abs/2408.10285) find
  72. Kevin Yu, Jihye Roh, Ziang Li, Wenhao Gao, Runzhong Wang, and Connor Coley. 2024. Double-ended synthesis planning with goal-constrained bidirectional search. Advances in Neural Information Processing Systems, 37:112919–112949. find
  73. Chonghuan Zhang, Qianghua Lin, Biwei Zhu, Haopeng Yang, Xiao Lian, Hao Deng, Jiajun Zheng, and Kuangbiao Liao. 2025a. Synask: unleashing the power of large language models in organic synthesis. Chemical science, 16(1):43–56. find
  74. Di Zhang, Wei Liu, Qian Tan, Jingdan Chen, Hang Yan, Yuliang Yan, Jiatong Li, Weiran Huang, Xiangyu Yue, Wanli Ouyang, and 1 others. 2024. Chemllm: A chemical large language model. arXiv preprint arXiv:2402.06852. find
  75. Situo Zhang, Hanqi Li, Lu Chen, Zihan Zhao, Xuanze Lin, Zichen Zhu, Bo Chen, Xin Chen, and Kai Yu. 2025b. Reasoning-driven retrosynthesis prediction with large language models via reinforcement learning. arXiv preprint arXiv:2507.17448. — [arXiv:2507.17448](https://arxiv.org/abs/2507.17448) find
  76. Xuefeng Zhang, Haowei Lin, Muhan Zhang, Yuan Zhou, and Jianzhu Ma. 2025c. A data-driven group retrosynthesis planning model inspired by neurosymbolic programming. Nature Communications, 16(1):192. find
  77. Dengwei Zhao, Shikui Tu, and Lei Xu. 2024. Efficient retrosynthetic planning with mcts exploration enhanced a* search. Communications Chemistry, 7(1):52. find
  78. Weihe Zhong, Ziduo Yang, and Calvin Yu-Chian Chen. 2023. Retrosynthesis prediction using an end-to-end graph generative architecture for molecular graph editing. Nature Communications, 14(1):3009. find
  79. Zipeng Zhong, Jie Song, Zunlei Feng, Tiantao Liu, Lingxiang Jia, Shaolun Yao, Min Wu, Tingjun Hou, and Mingli Song. 2022. Root-aligned smiles: a tight representation for chemical reaction prediction. Chemical Science, 13(31):9023–9034. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/song-2026-aot-efficient-synthesis-planning-llm/