{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T03:55:30Z","timestamp":1781582130036,"version":"3.54.5"},"reference-count":34,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Science &amp; Technology Fundamental Resources Investigation Program","award":["2022FY101200"],"award-info":[{"award-number":["2022FY101200"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Traditional Chinese medicine (TCM), as a vital component of traditional healthcare systems, relies heavily on its chemical constituents, which serve as a bridge between ancient therapeutic theories and modern biomedical science. Efficient access to compound-related information is crucial for promoting the modernization and scientific understanding of TCM. However, existing approaches primarily rely on fragmented databases and literature-based retrieval methods, which suffer from low intelligence, poor data integration, and limited retrieval efficiency.This study presents a novel AI agent-based retrieval system tailored for compound information in TCM. The core innovation of the system lies in its hybrid retrieval-augmented generation framework, which seamlessly combines structured database queries with semantic vector retrieval. Furthermore, it integrates knowledge from three complementary sources\u2014locally built knowledge bases, domain-specific APIs, and open web search\u2014allowing for comprehensive coverage and adaptive handling of diverse natural language queries. Experiments conducted on a benchmark dataset of 150 compound-related queries demonstrate that the system achieves a peak accuracy of 96.67% across multiple mainstream LLMs. Ablation studies further reveal that removing either the hybrid RAG or multi-source knowledge module leads to a notable accuracy decline, while the full system outperforms typical RAG baselines by over 25%. These results confirm the effectiveness and robustness of the proposed architecture in TCM compound retrieval, and highlight the advantage of combining structured matching with dynamic knowledge access in specialized biomedical applications.<\/jats:p>","DOI":"10.3390\/info16070543","type":"journal-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T03:33:25Z","timestamp":1750995205000},"page":"543","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An AI Agent-Based System for Retrieving Compound Information in Traditional Chinese Medicine"],"prefix":"10.3390","volume":"16","author":[{"given":"Feifan","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianjin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Metrology of Hebei Province, Shijiazhuang 050031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4629-8626","authenticated-orcid":false,"given":"Xingchuang","family":"Xiong","sequence":"additional","affiliation":[{"name":"Center for Metrology Scientific Data, National Institute of Metrology, Beijing 100029, China"},{"name":"National Metrology Data Center, Beijing 100029, China"},{"name":"Key Laboratory of Metrology Digitalization and Digital Metrology, State Administration for Market Regulation, Beijing 100029, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1142\/S0192415X19500253","article-title":"The Role of Chinese Medicine in Health Maintenance and Disease Prevention: Application of Constitution Theory","volume":"47","author":"Li","year":"2019","journal-title":"Am. J. Chin. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1142\/S0192415X19500629","article-title":"Application of Chinese Medicine in Acute and Critical Medical Conditions","volume":"47","author":"Luo","year":"2019","journal-title":"Am. J. Chin. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.jep.2016.05.025","article-title":"Traditional Chinese medicine formulas for the treatment of osteoporosis: Implication for antiosteoporotic drug discovery","volume":"189","author":"Zhang","year":"2016","journal-title":"J. Ethnopharmacol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"107824","DOI":"10.1016\/j.pharmthera.2021.107824","article-title":"Functional metabolomics innovates therapeutic discovery of traditional Chinese medicine derived functional compounds","volume":"224","author":"Wang","year":"2021","journal-title":"Pharmacol. Ther."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1958","DOI":"10.1002\/cam4.2108","article-title":"Traditional Chinese medicine as a cancer treatment: Modern perspectives of ancient but advanced science","volume":"8","author":"Xiang","year":"2019","journal-title":"Cancer Med."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1217","DOI":"10.1038\/nm.2471","article-title":"The discovery of artemisinin (qinghaosu) and gifts from Chinese medicine","volume":"17","author":"Tu","year":"2011","journal-title":"Nat. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.arcmed.2007.09.011","article-title":"Chinese Medicine and Its Modernization Demands","volume":"39","author":"Li","year":"2008","journal-title":"Arch. Med. Res."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Zhang, Y., Lin, W., and Wu, Q. (2024, January 3\u20136). How Can We Design a Standardized and Efficient Health Data Management System for Large-Scale Heterogeneous TCM Data?. Proceedings of the 2024 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Lisbon, Portugal.","DOI":"10.1109\/BIBM62325.2024.10822299"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"D1404","DOI":"10.1093\/nar\/gkae1037","article-title":"HERB 2.0: An updated database integrating clinical and experimental evidence for traditional Chinese medicine","volume":"53","author":"Gao","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"D1117","DOI":"10.1093\/nar\/gkx1028","article-title":"TCMID 2.0: A comprehensive resource for TCM","volume":"46","author":"Huang","year":"2018","journal-title":"Nucleic Acids Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"D976","DOI":"10.1093\/nar\/gky987","article-title":"ETCM: An encyclopaedia of traditional Chinese medicine","volume":"47","author":"Xu","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, R., Zhu, X., Bai, H., and Ning, K. (2019). Network Pharmacology Databases for Traditional Chinese Medicine: Review and Assessment. Front. Pharmacol., 10.","DOI":"10.3389\/fphar.2019.00123"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"121101","DOI":"10.1007\/s11432-024-4222-0","article-title":"The rise and potential of large language model based agents: A survey","volume":"68","author":"Xi","year":"2025","journal-title":"Sci. China Inf. Sci."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, A., Deng, Y., Lin, Y., Chen, X., Wen, J.R., and Chua, T.S. (2024, January 14\u201318). Large Language Model Powered Agents for Information Retrieval. Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2024; SIGIR \u201924, Washington, DC, USA.","DOI":"10.1145\/3626772.3661375"},{"key":"ref_15","unstructured":"Singh, A., Ehtesham, A., Kumar, S., and Khoei, T.T. (2025). Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"giae082","DOI":"10.1093\/gigascience\/giae082","article-title":"Knowledge graph-based thought: A knowledge graph-enhanced LLM framework for pan-cancer question answering","volume":"14","author":"Feng","year":"2025","journal-title":"GigaScience"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Duan, Y., Zhou, Q., Li, Y., Qin, C., Wang, Z., Kan, H., and Hu, J. (2024). Research on a traditional Chinese medicine case-based question-answering system integrating large language models and knowledge graphs. Front. Med., 11.","DOI":"10.3389\/fmed.2024.1512329"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ahmed, M., Dorrah, M., Ashraf, A., Adel, Y., Elatrozy, A., Mohamed, B.E., and Gomaa, W. (2024, January 19\u201321). CodeQA: Advanced programming question-answering using LLM agent and RAG. Proceedings of the 2024 6th Novel Intelligent and Leading Emerging Sciences Conference (NILES), Giza, Egypt.","DOI":"10.1109\/NILES63360.2024.10753267"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Vakayil, S., Juliet, D.S., J, A., and Vakayil, S. (2024, January 19\u201320). RAG-based LLM chatbot using llama-2. Proceedings of the 2024 7th International Conference on Devices, Circuits and Systems (ICDCS), Coimbatore, India.","DOI":"10.1109\/ICDCS59278.2024.10561020"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"C07006","DOI":"10.1088\/1748-0221\/19\/07\/C07006","article-title":"Towards a RAG-based summarization for the electron ion collider","volume":"19","author":"Suresh","year":"2024","journal-title":"J. Instrum."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","article-title":"PubChem 2023 update","volume":"51","author":"Kim","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"ref_22","unstructured":"Commission, C.P. (2020). Pharmacopoeia of the People\u2019s Republic of China, Volume I, China Medical Science and Technology Press."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"W605","DOI":"10.1093\/nar\/gkv396","article-title":"PUG-SOAP and PUG-REST: Web services for programmatic access to chemical information in PubChem","volume":"43","author":"Kim","year":"2015","journal-title":"Nucleic Acids Res."},{"key":"ref_24","unstructured":"(2025, March 15). Tavily Search API. Available online: https:\/\/tavily.com\/."},{"key":"ref_25","unstructured":"(2025, May 13). Chemical Abstracts Service. CAS REGISTRY. Available online: https:\/\/www.cas.org\/cas-data\/cas-registry."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1186\/s13321-015-0068-4","article-title":"InChI, the IUPAC International Chemical Identifier","volume":"7","author":"Heller","year":"2015","journal-title":"J. Cheminform."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Xiao, S., Liu, Z., Zhang, P., Muennighoff, N., Lian, D., and Nie, J.Y. (2024). C-Pack: Packed Resources For General Chinese Embeddings. arXiv.","DOI":"10.1145\/3626772.3657878"},{"key":"ref_28","unstructured":"(2025, March 15). PubMed, Available online: https:\/\/pubmed.ncbi.nlm.nih.gov\/."},{"key":"ref_29","unstructured":"(2025, March 15). CNKI (China National Knowledge Infrastructure). Available online: https:\/\/www.cnki.net\/."},{"key":"ref_30","unstructured":"(2025, March 15). Inc, LangGenius Dify: Open-Source LLM Application Development Platform. Available online: https:\/\/github.com\/langgenius\/dify."},{"key":"ref_31","unstructured":"DeepSeek-AI, Liu, A., Feng, B., Xue, B., Wang, B., Wu, B., Lu, C., Zhao, C., Deng, C., and Zhang, C. (2025). DeepSeek-V3 Technical Report. arXiv."},{"key":"ref_32","unstructured":"Yang, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Li, C., Liu, D., Huang, F., and Wei, H. (2025). Qwen2.5 Technical Report. arXiv."},{"key":"ref_33","unstructured":"GLM Team, Zeng, A., Xu, B., Wang, B., Zhang, C., Yin, D., Zhang, D., Rojas, D., Feng, G., and Zhao, H. (2024). ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools. arXiv."},{"key":"ref_34","unstructured":"(2025, March 15). ByteDance. Doubao v1.5-Pro. Available online: https:\/\/seed.bytedance.com\/en\/special\/doubao_1_5_pro\/."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/543\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:59:15Z","timestamp":1760032755000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/543"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,26]]},"references-count":34,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["info16070543"],"URL":"https:\/\/doi.org\/10.3390\/info16070543","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,26]]}}}