TCM-Agent: Advancing Network Pharmacology and Herbal Medicine Discovery with LLM-Based Multi-Agent Systems

Xiting Wang; Yuanrong Wang; Wenqing Dong; Shanshan Guo; Kai Wang; Shuangshuang He; Yuqi Wang; Haorui Li; Jian Lyu; Meng Liu; Lantian Zhang; Yinghao Zhu; Yiyuan Peng; Liantao Ma; Yu Li

doi:10.1016/j.jpha.2026.101581

Article Contents

Article Navigation > Journal of Pharmaceutical Analysis > 2026 > Accepted Manu

Xiting Wang, Yuanrong Wang, Wenqing Dong, Shanshan Guo, Kai Wang, Shuangshuang He, Yuqi Wang, Haorui Li, Jian Lyu, Meng Liu, Lantian Zhang, Yinghao Zhu, Yiyuan Peng, Liantao Ma, Yu Li. TCM-Agent: Advancing Network Pharmacology and Herbal Medicine Discovery with LLM-Based Multi-Agent Systems[J]. Journal of Pharmaceutical Analysis. doi: 10.1016/j.jpha.2026.101581

Citation:

Xiting Wang, Yuanrong Wang, Wenqing Dong, Shanshan Guo, Kai Wang, Shuangshuang He, Yuqi Wang, Haorui Li, Jian Lyu, Meng Liu, Lantian Zhang, Yinghao Zhu, Yiyuan Peng, Liantao Ma, Yu Li. TCM-Agent: Advancing Network Pharmacology and Herbal Medicine Discovery with LLM-Based Multi-Agent Systems[J]. Journal of Pharmaceutical Analysis. doi: 10.1016/j.jpha.2026.101581

Citation:

Xiting Wang, Yuanrong Wang, Wenqing Dong, Shanshan Guo, Kai Wang, Shuangshuang He, Yuqi Wang, Haorui Li, Jian Lyu, Meng Liu, Lantian Zhang, Yinghao Zhu, Yiyuan Peng, Liantao Ma, Yu Li. TCM-Agent: Advancing Network Pharmacology and Herbal Medicine Discovery with LLM-Based Multi-Agent Systems[J]. Journal of Pharmaceutical Analysis. doi: 10.1016/j.jpha.2026.101581

PDF( 9648 KB)

TCM-Agent: Advancing Network Pharmacology and Herbal Medicine Discovery with LLM-Based Multi-Agent Systems

doi: 10.1016/j.jpha.2026.101581

1. Beijing University of Chinese Medicine, Beijing, 100029, China;
2. XiYuan Hospital, China Academy of Chinese Medical Sciences, Beijing, 100091, China;
3. Beijing Sijiqing Hospital, Beijing,100089, China;
4. Department of Mathematics, KTH Royal Institute of Technology, Stockholm, 10044, Sweden;
5. National Engineering Research Center for Software Engineering, Peking University, Beijing, 100091, China

Funds:

This work was supported by the National Natural Science Foundation of China (Grant Nos.: 82474223, 82205101, and 62402017), the Beijing Natural Science Foundation (Grant No.: 7254501), Beijing Traditional Chinese Medicine Science and Technology Development Fund (Grant No.: BJZYZD-2025-13), the Noncommunicable Chronic Diseases-National Science and Technology Major Project (Project Nos.: 2024ZD0522100 and 2024ZD0522106), Haidian District Health Development Scientific Research Cultivation Program (Program No.: HP2023-50-202001), the Special Fund for Health Development Research of the Capital (Grant No.: 2024-4-4176), the Peking University Clinical Medicine Plus X (Grant No.: PKU2025PKULCXQ024), and the Pilot Program-Key Technologies Project (Project No.: 2024YXXLHGG007).

Received Date: Jun. 23, 2025
Accepted Date: Feb. 07, 2026
Rev Recd Date: Feb. 04, 2026
Available Online: Feb. 12, 2026

Abstract

Abstract

Network pharmacology has emerged as a pivotal approach for deciphering the complex “multi-component, multi-target” mechanisms underlying traditional Chinese medicine (TCM). However, despite extensive research efforts, a comprehensive and intelligent automated analytical framework remains elusive. Large language model (LLM)-based intelligent agent systems demonstrate robust capabilities in semantic understanding, logical inference, and task orchestration. In this study, we present the first LLM-powered multi-agent system specifically designed for network pharmacology and herbal medicine research, namely TCM-Agent. The system demonstrates core capabilities including autonomous knowledge reasoning, data analysis, interactive visualization, as well as literature retrieval and validation. Benchmark evaluations across 100 validated TCM studies demonstrated that the TCM-Agent demonstrated competitive performance in answer accuracy, literature retrieval precision, and computational efficiency. Crucially, the TCM-Agent system exhibited robust and high performance across evaluated foundation model platforms (DeepSeek-v3, Qwen-plus, and GLM-4-plus). Furthermore, no significant differences were observed across the various foundation model platforms, indicating the system’s adaptability and stability when integrated with different LLM. These findings establish TCM-Agent as a robust system that provides an advanced framework, facilitating standardization, intelligent transformation, and evidence-based methodologies in network pharmacology and herbal medicine research. Consequently, TCM-Agent enhances the intelligent analysis of TCM formulas, aids in bioactive compound discovery, and establishes foundational infrastructure for next-generation network pharmacology, thereby advancing research in the field.
- Large language model,
- LLM-based agent,
- Network pharmacology,
- Herbal medicine discovery,
- Traditional Chinese medicine

FullText(HTML)

References(40)

References

[1]	Hao P, Jiang F, Cheng J, Ma L, Zhang Y, Zhao Y. Traditional Chinese Medicine for Cardiovascular Disease: Evidence and Potential Mechanisms. J Am Coll Cardiol. 2017 Jun 20;69(24):2952-2966.
[2]	Zhang HY, Tian JX, Lian FM, Li M, Liu WK, Zhen Z, Liao JQ, Tong XL. Therapeutic mechanisms of traditional Chinese medicine to improve metabolic diseases via the gut microbiota. Biomed Pharmacother. 2021 Jan;133:110857.
[3]	Wei L, Zhang L, Zhang Y, Yan L, Liu B, Cao Z, Zhao N, He X, Li L, Lu C. Intestinal Escherichia coli and related dysfunction as potential targets of Traditional Chinese Medicine for respiratory infectious diseases. J Ethnopharmacol. 2023 Sep 15;313:116381.
[4]	Yang HY, Liu ML, Luo P, Yao XS, Zhou H. Network pharmacology provides a systematic approach to understanding the treatment of ischemic heart diseases with traditional Chinese medicine. Phytomedicine. 2022 Sep,104:154268.
[5]	Hopkins AL. Network pharmacology: the next paradigm in drug discovery. Nat Chem Biol. 2008 Nov;4(11):682-690.
[6]	Zhai Y, Liu L, Zhang F, Chen X, Wang H, Zhou J, Chai K, Liu J, Lei H, Lu P, Guo M, Guo J, Wu J. Network pharmacology: a crucial approach in traditional Chinese medicine research. Chin Med. 2025 Jan 12,20(1):8.
[7]	Chen X, Zhou H, Liu YB, Wang JF, Li H, Ung CY, Han LY, Cao ZW, Chen YZ. Database of traditional Chinese medicine and its application to studies of mechanism and to prescription validation. Br J Pharmacol. 2006 Dec,149(8):1092-1103.
[8]	Ru J, Li P, Wang J, Zhou W, Li B, Huang C, Li P, Guo Z, Tao W, Yang Y, Xu X, Li Y, Wang Y, Yang L. TCMSP: a database of systems pharmacology for drug discovery from herbal medicines. J Cheminform. 2014 Apr 16,6:13.
[9]	Huang L, Xie D, Yu Y, Liu H, Shi Y, Shi T, Wen C. TCMID 2.0: a comprehensive resource for TCM. Nucleic Acids Res. 2018 Jan 4,46(D1):D1117-D1120.
[10]	Kong X, Liu C, Zhang Z, Cheng M, Mei Z, Li X, Liu P, Diao L, Ma Y, Jiang P, Kong X, Nie S, Guo Y, Wang Z, Zhang X, Wang Y, Tang L, Guo S, Liu Z, Li D. BATMAN-TCM 2.0: an enhanced integrative database for known and predicted interactions between traditional Chinese medicine ingredients and target proteins. Nucleic Acids Res. 2024 Jan 5;52(D1):D1110-D1120.
[11]	Xu HY, Zhang YQ, Liu ZM, Chen T, Lv CY, Tang SH, Zhang XB, Zhang W, Li ZY, Zhou RR, Yang HJ, Wang XJ, Huang LQ. ETCM: an encyclopaedia of traditional Chinese medicine. Nucleic Acids Res. 2019 Jan 8,47(D1):D976-D982.
[12]	Fang S, Dong L, Liu L, Guo J, Zhao L, Zhang J, Bu D, Liu X, Huo P, Cao W, Dong Q, Wu J, Zeng X, Wu Y, Zhao Y. HERB: a high-throughput experiment- and reference-guided database of traditional Chinese medicine. Nucleic Acids Res. 2021 Jan 8,49(D1):D1197-D1206.
[13]	Lv Q, Chen G, He H, Yang Z, Zhao L, Zhang K, Chen CY. TCMBank-the largest TCM database provides deep learning-based Chinese-Western medicine exclusion prediction. Signal Transduct Target Ther. 2023 Mar 31,8(1):127.
[14]	Li X, Ren J, Zhang W, Zhang Z, Yu J, Wu J, Sun H, Zhou S, Yan K, Yan X, Wang W. LTM-TCM: A comprehensive database for the linking of Traditional Chinese Medicine with modern medicine at molecular and phenotypic levels. Pharmacol Res. 2022 Apr,178:106185.
[15]	Noor F, Tahir Ul Qamar M, Ashfaq UA, Albutti A, Alwashmi ASS, Aljasir MA. Network Pharmacology Approach for Medicinal Plants: Review and Assessment. Pharmaceuticals (Basel). 2022 May 4;15(5):572.
[16]	P. Qiu, A. Mi, C. Hong, et al. An Integrated Network Pharmacology Approach Reveals that Ampelopsis Grossedentata Improves Alcoholic Liver Disease via TLR4/NF-κB/MLKL pathway. Phytomedicine. 2024 Sep;132:155658. PMID: 38981149.
[17]	Wang X, Wang ZY, Zheng JH, Li S. TCM network pharmacology: A new trend towards combining computational, experimental and clinical approaches. Chin J Nat Med. 2021 Jan;19(1):1-11.
[18]	Noor F, Asif M, Ashfaq UA, Qasim M, Tahir Ul Qamar M. Machine learning for synergistic network pharmacology: a comprehensive overview. Brief Bioinform. 2023 May 19;24(3):bbad120.
[19]	Li L, Yang L, Yang L, He C, He Y, Chen L, Dong Q, Zhang H, Chen S, Li P. Network pharmacology: a bright guiding light on the way to explore the personalized precise medication of traditional Chinese medicine. Chin Med. 2023 Nov 8;18(1):146.
[20]	Lee WY, Lee CY, Kim YS, Kim CE. The Methodological Trends of Traditional Herbal Medicine Employing Network Pharmacology. Biomolecules. 2019 Aug 13,9(8):362.
[21]	J.Y. Wang, M. Kabakova, E. Austin, Jagdeo J. Network pharmacology as a platform for drug discovery for hypertrophic scars. Br J Dermatol. 2024 Sep 18;191(4):484-485. PMID: 38924727.
[22]	Zhang K, Yang X, Wang Y, Yu Y, Huang N, Li G, Li X, Wu JC, Yang S. Artificial intelligence in drug development. Nat Med. 2025 Jan;31(1):45-59.
[23]	Wang Y, Wu Z, Yao J, Su J. TDAG: A multi-agent framework based on dynamic Task Decomposition and Agent Generation. Neural Netw. 2025 May;185:107200.
[24]	Gao B, Huang Y, Liu Y, et al. PharmAgents: Building a Virtual Pharma with Large Language Model Agents[J]. arXiv preprint arXiv:2503.22164, 2025.
[25]	Wang H, He Y, Coelho P P, et al. SpatialAgent: An Autonomous AI Agent for Spatial Biology[J]. bioRxiv, 2025: 2025.04. 03.646459.
[26]	Wei Xu, Gang Luo, Weiyu Meng, Xiaobing Zhai, Keli Zheng, Ji Wu, Yanrong Li, Abao Xing, Junrong Li, Zhifan Li, Ke Zheng, Kefeng Li, MRAgent: an LLM-based automated agent for causal knowledge discovery in disease via Mendelian randomization, Briefings in Bioinformatics, Volume 26, Issue 2, March 2025, bbaf140.
[27]	Omiye JA, Gui H, Rezaei SJ, Zou J, Daneshjou R. Large Language Models in Medicine: The Potentials and Pitfalls : A Narrative Review. Ann Intern Med. 2024 Feb;177(2):210-220.
[28]	Tripathi S, Gabriel K, Tripathi PK, Kim E. Large language models reshaping molecular biology and drug development. Chem Biol Drug Des. 2024 Jun;103(6):e14568.
[29]	Zhou Y, Zhang Y, Zhao D, Yu X, Shen X, Zhou Y, Wang S, Qiu Y, Chen Y, Zhu F. TTD: Therapeutic Target Database describing target druggability information. Nucleic Acids Res. 2024 Jan 5;52(D1):D1465-D1477.
[30]	Sharon L Freshour, Susanna Kiwala, Kelsy C Cotto, Adam C Coffman, Joshua F McMichael, Jonathan J Song, Malachi Griffith, Obi L Griffith, Alex H Wagner, Integration of the Drug-Gene Interaction Database (DGIdb 4.0) with open crowdsource efforts, Nucleic Acids Research, Volume 49, Issue D1, 8 January 2021, Pages D1144-D1151.
[31]	Fu L, Shi S, Yi J, Wang N, He Y, Wu Z, Peng J, Deng Y, Wang W, Wu C, Lyu A, Zeng X, Zhao W, Hou T, Cao D. ADMETlab 3.0: an updated comprehensive online ADMET prediction platform enhanced with broader coverage, improved performance, API functionality and decision support. Nucleic Acids Res. 2024 Jul 5;52(W1):W422-W431.
[32]	Wu L, Zhang Q, Mo W, Feng J, Li S, Li J, Liu T, Xu S, Wang W, Lu X, Yu Q, Chen K, Xia Y, Lu J, Xu L, Zhou Y, Fan X, Guo C. Quercetin prevents hepatic fibrosis by inhibiting hepatic stellate cell activation and reducing autophagy via the TGF-β1/Smads and PI3K/Akt pathways. Sci Rep. 2017 Aug 24;7(1):9289.
[33]	Liu Y, He CY, Yang XM, Chen WC, Zhang MJ, Zhong XD, Chen WG, Zhong BL, He SQ, Sun HT. Paeoniflorin Coordinates Macrophage Polarization and Mitigates Liver Inflammation and Fibrogenesis by Targeting the NF-[Formula: see text]B/HIF-1α Pathway in CCl4-Induced Liver Fibrosis. Am J Chin Med. 2023;51(5):1249-1267.
[34]	Li X, Liu Z, Liao J, Chen Q, Lu X, Fan X. Network pharmacology approaches for research of Traditional Chinese Medicines. Chin J Nat Med. 2023 May,21(5):323-332.
[35]	Zhao L, Zhang H, Li N, Chen J, Xu H, Wang Y, Liang Q. Network pharmacology, a promising approach to reveal the pharmacology mechanism of Chinese medicine formula. J Ethnopharmacol. 2023 Jun 12,309:116306.
[36]	Zhang R, Zhu X, Bai H, Ning K. Network Pharmacology Databases for Traditional Chinese Medicine: Review and Assessment. Front Pharmacol. 2019 Feb 21,10:123.
[37]	Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW. Large language models in medicine. Nat Med. 2023 Aug,29(8):1930-1940.
[38]	Li H, Zhang R, Lee YC, Kraut RE, Mohr DC. Systematic review and meta-analysis of AI-based conversational agents for promoting mental health and well-being. NPJ Digit Med. 2023 Dec 19,6(1):236.
[39]	Chen X, Yi H, You M, Liu W, Wang L, Li H, Zhang X, Guo Y, Fan L, Chen G, Lao Q, Fu W, Li K, Li J. Enhancing diagnostic capability with multi-agents conversational large language models. NPJ Digit Med. 2025 Mar 13,8(1):159.
[40]	Zhou J, Zhang B, Li G, Chen X, Li H, Xu X, Chen S, He W, Xu C, Liu L, Gao X. An AI Agent for Fully Automated Multi-Omic Analyses. Adv Sci (Weinh). 2024 Nov;11(44):e2407094.