{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T19:16:43Z","timestamp":1788290203100,"version":"build-2803163510"},"reference-count":44,"publisher":"American Chemical Society (ACS)","issue":"34","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82371901"],"award-info":[{"award-number":["82371901"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFC3306605"],"award-info":[{"award-number":["2024YFC3306605"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Basic Research Project of Guangzhou","doi-asserted-by":"publisher","award":["202201011630"],"award-info":[{"award-number":["202201011630"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/na","name":"Science and Technology Program of the Ministry of Public Security of China","doi-asserted-by":"publisher","award":["2023JSM07"],"award-info":[{"award-number":["2023JSM07"]}],"id":[{"id":"10.13039\/na","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Artificial intelligence in molecular science must move beyond pattern recognition toward chemically valid and interpretable reasoning. We present a task-adaptive large reasoning model that integrates chemical knowledge through a synergistic multispecialist architecture, chain-of-thought supervision, and molecule-informed reinforcement learning. Task-conditioned routing coordinates prediction and inference specialists across 10 molecular tasks spanning molecular description and generation, nomenclature translation, property prediction, and reaction prediction. The model outperforms more than 20 general-purpose and molecular large language models, improves aggregate performance over the base model by 50.3%, and surpasses the leading molecular multitask baseline on most tasks. Analyses of specialist representations and reasoning pathways reveal task-specific adaptation while retaining interpretable chemical inference. A case study further demonstrates an integrated workflow for central nervous system candidate generation, property screening, molecular interpretation, and retrosynthetic planning. These results demonstrate a versatile multitask framework for knowledge-guided molecular reasoning and design, with the potential to serve as a core task engine for future molecular science agents.<\/jats:p>","DOI":"10.1021\/acs.jpclett.6c02427","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T07:01:56Z","timestamp":1786950116000},"page":"9831-9843","source":"Crossref","is-referenced-by-count":0,"title":["A Multitask\nLarge Reasoning Model for Molecular Science"],"prefix":"10.1021","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6130-6968","authenticated-orcid":true,"given":"Pengfei","family":"Liu","sequence":"first","affiliation":[{"name":"Guangzhou Key Laboratory of Forensic Multi-Omics for Precision Identification, Southern Medical University , , ,","place":["Guangzhou, Guangdong, China, 510515"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Ge","sequence":"additional","affiliation":[{"name":"Tsinghua University , , , ,","place":["Shenzhen, Guangdong, China, 518000"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobo","family":"Wang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Psychoactive Substances Monitoring and Safety, Anti-Drug Technology Center of Guangdong Province (National Anti-Drug Laboratory Guangdong Regional Center) , ,","place":["Guangzhou, China, 510230"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Psychoactive Substances Monitoring and Safety, Anti-Drug Technology Center of Guangdong Province (National Anti-Drug Laboratory Guangdong Regional Center) , ,","place":["Guangzhou, China, 510230"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Tao","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University , , , ,","place":["Guangzhou, Guangdong, China, 510006"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Li","sequence":"additional","affiliation":[{"name":"Xiyuan Hospital, China Academy of Chinese Medical Sciences , , ,","place":["Beijing, China, 100091"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Liu","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Psychoactive Substances Monitoring and Safety, Anti-Drug Technology Center of Guangdong Province (National Anti-Drug Laboratory Guangdong Regional Center) , ,","place":["Guangzhou, China, 510230"]},{"name":"Jinan University , , ,","place":["Guangzhou, China, 510632"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7699-4820","authenticated-orcid":true,"given":"Ling","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangzhou Key Laboratory of Forensic Multi-Omics for Precision Identification, Southern Medical University , , ,","place":["Guangzhou, Guangdong, China, 510515"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4104-3790","authenticated-orcid":true,"given":"Zhixiang","family":"Ren","sequence":"additional","affiliation":[{"name":"Shanghai Smart Logic Technology , ,","place":["Shanghai, China, 200443"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"2026090114435425400_cit1","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1038\/s42256-020-00236-4","article-title":"Drug Discovery with Explainable Artificial\nIntelligence","volume":"2","author":"Jime\u0301nez-Luna","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"2026090114435425400_cit2","doi-asserted-by":"publisher","first-page":"3399","DOI":"10.1007\/s11831-020-09506-1","article-title":"Artificial Intelligence\nin Materials Modeling and Design","volume":"28","author":"Huang","year":"2021","journal-title":"Arch. Comput.\nMethods Eng."},{"key":"2026090114435425400_cit3","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1038\/s42256-025-01066-y","article-title":"Large Language Models to Accelerate Organic Chemistry Synthesis","volume":"7","author":"Zhang","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026090114435425400_cit4","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1603","article-title":"A Review of Molecular\nRepresentation\nin the Age of Machine Learning","volume":"12","author":"Wigh","year":"2022","journal-title":"Wiley Interdiscip.\nRev.: Comput. Mol. Sci."},{"key":"2026090114435425400_cit5","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1038\/s42256-025-01087-7","article-title":"Kolmogorov\u2013Arnold\nGraph Neural Networks for Molecular Property Prediction","volume":"7","author":"Li","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026090114435425400_cit6","unstructured":"Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A. N.; Kaiser, \u0141.; Polosukhin, I.\n          Attention Is All You Need.\n          Advances in Neural Information Processing Systems 30; 2017; pp 5998\u20136008."},{"key":"2026090114435425400_cit7","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a\nChemical Language and Information System. 1. Introduction to Methodology\nand Encoding Rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"2026090114435425400_cit8","doi-asserted-by":"crossref","unstructured":"Devlin, J.; Chang, M.-W.; Lee, K.; Toutanova, K. In  Proceedings\nof the 2019 Conference of\nthe North American Chapter of the Association for Computational Linguistics:\nHuman Language Technologies, 2019; pp 4171\u20134186.","DOI":"10.18653\/v1\/N19-1423"},{"key":"2026090114435425400_cit9","unstructured":"Radford, A.; Wu, J.; Child, R.; Luan, D.; Amodei, D.; Sutskever, I.\n          Language\nModels Are Unsupervised Multitask Learners.\n          Technical Report, 2019, https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf. (accessed on Aug 3, 2026)."},{"key":"2026090114435425400_cit10","first-page":"1","article-title":"Exploring\nthe Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"2026090114435425400_cit11","unstructured":"Optimizing\nLanguage Models for Dialogue,  OpenAI, accessed 2026-08-03, 2022; https:\/\/openai.com\/index\/chatgpt\/."},{"key":"2026090114435425400_cit12","doi-asserted-by":"crossref","unstructured":"Edwards, C.; Lai, T.; Ros, K.; Honke, G.; Cho, K.; Ji, H. In  Proceedings of the 2022 Conference on\nEmpirical Methods in Natural\nLanguage Processing (EMNLP), 2022; pp 375\u2013413.","DOI":"10.18653\/v1\/2022.emnlp-main.26"},{"key":"2026090114435425400_cit13","first-page":"1216","volume-title":"Findings of the Association for\nComputational Linguistics","author":"Pei","year":"2024"},{"key":"2026090114435425400_cit14","volume-title":"Nomenclature of Organic\nChemistry: IUPAC Recommendations and Preferred Names 2013","author":"Favre","year":"2014"},{"key":"2026090114435425400_cit15","doi-asserted-by":"publisher","first-page":"108073","DOI":"10.1016\/j.compbiomed.2024.108073","article-title":"GIT-Mol: A Multi-Modal Large Language\nModel for Molecular Science with Graph, Image, and Text","volume":"171","author":"Liu","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"2026090114435425400_cit16","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1038\/s42256-023-00759-6","article-title":"Multi-Modal\nMolecule Structure\u2013Text Model for Text-Based Retrieval and\nEditing","volume":"5","author":"Liu","year":"2023","journal-title":"Nat. Mach. Intell."},{"key":"2026090114435425400_cit17","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1038\/s42256-025-00994-z","article-title":"Large Language\nModels for Scientific\nDiscovery in Molecular Property Prediction","volume":"7","author":"Zheng","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026090114435425400_cit18","doi-asserted-by":"publisher","first-page":"111112","DOI":"10.1016\/j.engappai.2025.111112","article-title":"A Self-Feedback Knowledge Elicitation\nApproach for\nChemical Reaction Predictions","volume":"156","author":"Liu","year":"2025","journal-title":"Eng. Appl. Artif.\nIntell."},{"key":"2026090114435425400_cit19","doi-asserted-by":"publisher","first-page":"858","DOI":"10.26599\/BDMA.2024.9020028","article-title":"Impact of\nDomain Knowledge and Multi-Modality on Intelligent\nMolecular Property Prediction: A Systematic Survey","volume":"7","author":"Kuang","year":"2024","journal-title":"Big Data Min. Anal."},{"key":"2026090114435425400_cit20","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1038\/s42256-024-00977-6","article-title":"A Quantitative Analysis of Knowledge-Learning\nPreferences\nin Large Language Models in Molecular Science","volume":"7","author":"Liu","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026090114435425400_cit21","unstructured":"Yu, B.; Baker, F. N.; Chen, Z.; Ning, X.; Sun, H. In  Proceedings of the First Conference on Language Modeling\n(COLM), 2024."},{"key":"2026090114435425400_cit22","unstructured":"Zhang, D.; Liu, W.; Tan, Q.; Chen, J.; Yan, H.; Yan, Y.; Li, J.; Huang, W.; Yue, X.; Ouyang, W.; et al., ChemLLM: A Chemical\nLarge Language Model, submitted 2024-02-10; accessed\n2026-08-03, 2024, arXiv: 2402.06852 [cs.AI], https:\/\/arxiv.org\/abs\/2402.06852."},{"key":"2026090114435425400_cit23","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.1038\/s42256-025-01064-0","article-title":"Advancing Biomolecular\nUnderstanding and Design Following\nHuman Instructions","volume":"7","author":"Zhuang","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026090114435425400_cit24","unstructured":"Jaech, A.; Kalai, A.; Lerer, A.; Richardson, A.; El-Kishky, A.; Low, A.; Helyar, A.; Madry, A.; Beutel, A.; Carney, A.; et al., OpenAI o1 System Card, submitted 2024-12-21;\naccessed 2026-08-03, 2024, arXiv: 2412.16720 [cs.AI], https:\/\/arxiv.org\/abs\/2412.16720."},{"key":"2026090114435425400_cit25","unstructured":"Guo, D.; Yang, D.; Zhang, H.; Song, J.; Zhang, R.; Xu, R.; Zhu, Q.; Ma, S.; Wang, P.; Bi, X.; et al., DeepSeek-R1: Incentivizing\nReasoning Capability in LLMs via Reinforcement Learning, submitted\n2025-01-22; accessed 2026-08-03, 2025, arXiv: 2501.12948\n[cs.CL], https:\/\/arxiv.org\/abs\/2501.12948."},{"key":"2026090114435425400_cit26","unstructured":"Shazeer, N.; Mirhoseini, A.; Maziarz, K.; Davis, A.; Le, Q.; Hinton, G.; Dean, J. In  Proceedings of the\n5th International Conference on Learning\nRepresentations; ICLR: 2017."},{"key":"2026090114435425400_cit27","unstructured":"Wang, E.; Schmidgall, S.; Jaeger, P. F.; Zhang, F.; Pilgrim, R.; Matias, Y.; Barral, J.; Fleet, D.; Azizi, S.\n          TxGemma: Efficient and Agentic LLMs\nfor Therapeutics, submitted 2025\u201304\u201308;\naccessed 2026\u201308\u201303, 2025, arXiv: 2504.06196 [cs.AI], https:\/\/arxiv.org\/abs\/2504.06196."},{"key":"2026090114435425400_cit28","doi-asserted-by":"crossref","first-page":"24824","DOI":"10.52202\/068431-1800","article-title":"Chain-of-Thought Prompting\nElicits Reasoning in Large Language Models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2026090114435425400_cit29","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/C7SC02664A","article-title":"MoleculeNet: A Benchmark\nfor Molecular Machine Learning","volume":"9","author":"Wu","year":"2018","journal-title":"Chem. Sci."},{"key":"2026090114435425400_cit30","unstructured":"Banerjee, S.; Lavie, A. In  Proceedings of the ACL Workshop\non Intrinsic and Extrinsic Evaluation Measures for Machine Translation\nand\/or Summarization, 2005; pp 65\u201372."},{"key":"2026090114435425400_cit31","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1021\/ci010132r","article-title":"Reoptimization of\nMDL Keys for Use in Drug Discovery","volume":"42","author":"Durant","year":"2002","journal-title":"J. Chem.\nInf. Comput. Sci."},{"key":"2026090114435425400_cit32","unstructured":"Liu, A.; Feng, B.; Xue, B.; Wang, B.; Wu, B.; Lu, C.; Zhao, C.; Deng, C.; Zhang, C.; Ruan, C.; et al., DeepSeek-V3 Technical\nReport, submitted 2024-12-27; accessed 2026-08-03,\n2024, arXiv: 2412.19437 [cs.CL], https:\/\/arxiv.org\/abs\/2412.19437."},{"key":"2026090114435425400_cit33","unstructured":"Comanici, G.; Bieber, E.; Schaekermann, M.; Pasupat, I.; Sachdeva, N.; Dhillon, I.; Blistein, M.; Ram, O.; Zhang, D.; Rosen, E.; et al., Gemini 2.5: Pushing the Frontier with\nAdvanced Reasoning, Multimodality, Long Context, and Next Generation\nAgentic Capabilities, submitted 2025-07-07; accessed\n2026-08-03, 2025, arXiv: 2507.06261 [cs.CL], https:\/\/arxiv.org\/abs\/2507.06261."},{"key":"2026090114435425400_cit34","unstructured":"Anthropic Claude 3.5 Sonnet Model Card Addendum.\n          ;  Model Card Addendum, accessed 2026-08-03; Anthropic, 2024, https:\/\/www-cdn.anthropic.com\/fed9cc193a14b84131812372d8d5857f8f304c52\/Model_Card_Claude_3_Addendum.pdf."},{"key":"2026090114435425400_cit35","unstructured":"OpenAI OpenAI o3 and o4-mini System Card; System\nCard, accessed 2026\u201308\u201303; OpenAI, 2025, https:\/\/cdn.openai.com\/pdf\/2221c875-02dc-4789-800b-e7758f3722c1\/o3-and-o4-mini-system-card.pdf."},{"key":"2026090114435425400_cit36","unstructured":"Yang, A.; Li, A.; Yang, B.; Zhang, B.; Hui, B.; Zheng, B.; Yu, B.; Gao, C.; Huang, C.; Lv, C.; et al., Qwen3 Technical Report, submitted 2025\u201305\u201314;\naccessed 2026\u201308\u201303,\n2025, arXiv: 2505.09388 [cs.CL], https:\/\/arxiv.org\/abs\/2505.09388."},{"key":"2026090114435425400_cit37","unstructured":"Mistral AI Un Ministral, des Ministraux; accessed 2026-08-03,\n2024, https:\/\/mistral.ai\/news\/ministraux."},{"key":"2026090114435425400_cit38","unstructured":"Meta AI The Llama 4 Herd: The Beginning\nof a New Era of Natively\nMultimodal AI Innovation, Meta AI, accessed 2026\u201308\u201303,\n2025, https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/."},{"key":"2026090114435425400_cit39","doi-asserted-by":"publisher","first-page":"861","DOI":"10.21105\/joss.00861","article-title":"UMAP: Uniform\nManifold Approximation and Projection","volume":"3","author":"McInnes","year":"2018","journal-title":"J. Open\nSource Softw."},{"key":"2026090114435425400_cit40","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1016\/j.biopsych.2024.03.014","article-title":"Muscarinic Receptor Activators as\nNovel Treatments\nfor Schizophrenia","volume":"96","author":"Paul","year":"2024","journal-title":"Biol. Psychiatry"},{"key":"2026090114435425400_cit41","unstructured":"Gottweis, J.; Weng, W.-H.; Daryin, A.; Tu, T.; Sirkovic, P.; Myaskovsky, A.; Glowaty, G.; Weissenberger, F.; Orlandi, A.; Popovici, D.; et al., Accelerating\nScientific Discovery with Co-Scientist, submitted\n2025-02-26; accessed 2026-08-03, 2025, arXiv: 2502.18864 [cs.AI], https:\/\/arxiv.org\/abs\/2502.18864."},{"key":"2026090114435425400_cit42","unstructured":"Lu, C.; Lu, C.; Lange, R. T.; Foerster, J.; Clune, J.; Ha, D.\n          The AI Scientist: Towards Fully Automated\nOpen-Ended\nScientific Discovery, submitted 2024-08-12; accessed\n2026-08-03, 2024, arXiv: 2408.06292 [cs.AI], https:\/\/arxiv.org\/abs\/2408.06292."},{"key":"2026090114435425400_cit43","first-page":"2579","article-title":"Visualizing Data Using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"2026090114435425400_cit44","unstructured":"Hu, E. J.; Shen, Y.; Wallis, P.; Allen-Zhu, Z.; Li, Y.; Wang, S.; Wang, L.; Chen, W. In  Proceedings of the 10th International Conference on Learning\nRepresentations; ICLR: 2022."}],"container-title":["The Journal of Physical\nChemistry Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jpclett.6c02427","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jpclcd\/article-pdf\/17\/34\/9831\/66608825\/acs.jpclett.6c02427.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jpclcd\/article-pdf\/17\/34\/9831\/66608825\/acs.jpclett.6c02427.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T18:44:06Z","timestamp":1788288246000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jpclcd\/article\/17\/34\/9831\/5259570\/A-Multitask-Large-Reasoning-Model-for-Molecular"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":44,"journal-issue":{"issue":"34","published-online":{"date-parts":[[2026,8,17]]},"published-print":{"date-parts":[[2026,8,27]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jpclett.6c02427","relation":{},"ISSN":["1948-7185"],"issn-type":[{"value":"1948-7185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]}}}