E Liu, H Yang, S Sharma, M B van Leerdam, P Niu, M J VandeHaar, M Hostens
{"title":"代理是你所需要的一切:开拓使用代理人工智能,将大型语言模型纳入乳品科学。","authors":"E Liu, H Yang, S Sharma, M B van Leerdam, P Niu, M J VandeHaar, M Hostens","doi":"10.3168/jds.2025-26775","DOIUrl":null,"url":null,"abstract":"<p><p>Large language models (LLM) hold significant promise to transform dairy science by enhancing research interpretation, supporting decision making, and improving knowledge dissemination. However, without proper systematic design, LLM may generate irrelevant or factually inaccurate responses for domain-specific questions. Moreover, most existing LLM and related tools are not tailored to the needs of the dairy domain, limiting their practical application within the field. To demonstrate the feasibility and practical value of embracing LLM in dairy science, we developed a 2-component agentic system: (1) a decision-support chatbot grounded in the Journal of Dairy Science (JDS) for science-backed insights and (2) a natural language interface for interacting with academic models and visualizing prediction results. All publicly available JDS abstracts and associated metadata dating back to 1917 were compiled using the PubMed application programming interface, forming a scientific knowledge base that enables the chatbot to answer user questions. A retrieval-augmented generation framework was implemented to ensure that responses generated by LLaMA (a LLM developed by Meta) were well-grounded in peer-reviewed literature, with the 5 most relevant sources cited alongside each answer. To address questions beyond the coverage of JDS literature, a web search agent was incorporated into the system to retrieve supplementary information from external online sources. Grading agents, powered by Databricks Research Transformer X (DBRX; a LLM developed by Databricks), were incorporated to evaluate the credibility and relevance of LLM-generated content to mitigate the risk of misinformation or hallucinated responses. The second component of the system facilitates natural language interaction with MilkBot, a published Bayesian milk yield prediction model. After users submit questions in plain language, the system converts the question into model parameters for MilkBot, executes the model prediction, and uses the predicted output to generate visualizations. This work demonstrates the capability of LLM to serve as intuitive, user-friendly interfaces for dairy-specific models. To our knowledge, this is the first chatbot prototype that integrates large-scale information from scientific literature, web-based resources, and academic models, along with self-evaluation capability, to provide dairy-specific insights to scholars, consultants, and farmers. However, challenges remain to realize the full value of LLM-assisted decision making, such as the lack of region-specific data to tailor the answers to the local circumstances, the need for more robust measures to protect data security and privacy, and the need to integrate additional functions to enable more comprehensive decision support.</p>","PeriodicalId":354,"journal":{"name":"Journal of Dairy Science","volume":" ","pages":""},"PeriodicalIF":4.4000,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Agents are all you need: Pioneering the use of agentic artificial intelligence to embrace large language models into dairy science.\",\"authors\":\"E Liu, H Yang, S Sharma, M B van Leerdam, P Niu, M J VandeHaar, M Hostens\",\"doi\":\"10.3168/jds.2025-26775\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Large language models (LLM) hold significant promise to transform dairy science by enhancing research interpretation, supporting decision making, and improving knowledge dissemination. However, without proper systematic design, LLM may generate irrelevant or factually inaccurate responses for domain-specific questions. Moreover, most existing LLM and related tools are not tailored to the needs of the dairy domain, limiting their practical application within the field. To demonstrate the feasibility and practical value of embracing LLM in dairy science, we developed a 2-component agentic system: (1) a decision-support chatbot grounded in the Journal of Dairy Science (JDS) for science-backed insights and (2) a natural language interface for interacting with academic models and visualizing prediction results. All publicly available JDS abstracts and associated metadata dating back to 1917 were compiled using the PubMed application programming interface, forming a scientific knowledge base that enables the chatbot to answer user questions. A retrieval-augmented generation framework was implemented to ensure that responses generated by LLaMA (a LLM developed by Meta) were well-grounded in peer-reviewed literature, with the 5 most relevant sources cited alongside each answer. To address questions beyond the coverage of JDS literature, a web search agent was incorporated into the system to retrieve supplementary information from external online sources. Grading agents, powered by Databricks Research Transformer X (DBRX; a LLM developed by Databricks), were incorporated to evaluate the credibility and relevance of LLM-generated content to mitigate the risk of misinformation or hallucinated responses. The second component of the system facilitates natural language interaction with MilkBot, a published Bayesian milk yield prediction model. After users submit questions in plain language, the system converts the question into model parameters for MilkBot, executes the model prediction, and uses the predicted output to generate visualizations. This work demonstrates the capability of LLM to serve as intuitive, user-friendly interfaces for dairy-specific models. To our knowledge, this is the first chatbot prototype that integrates large-scale information from scientific literature, web-based resources, and academic models, along with self-evaluation capability, to provide dairy-specific insights to scholars, consultants, and farmers. However, challenges remain to realize the full value of LLM-assisted decision making, such as the lack of region-specific data to tailor the answers to the local circumstances, the need for more robust measures to protect data security and privacy, and the need to integrate additional functions to enable more comprehensive decision support.</p>\",\"PeriodicalId\":354,\"journal\":{\"name\":\"Journal of Dairy Science\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":4.4000,\"publicationDate\":\"2025-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Dairy Science\",\"FirstCategoryId\":\"97\",\"ListUrlMain\":\"https://doi.org/10.3168/jds.2025-26775\",\"RegionNum\":1,\"RegionCategory\":\"农林科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"AGRICULTURE, DAIRY & ANIMAL SCIENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Dairy Science","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.3168/jds.2025-26775","RegionNum":1,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"AGRICULTURE, DAIRY & ANIMAL SCIENCE","Score":null,"Total":0}
引用次数: 0
摘要
大型语言模型(LLM)通过加强研究解释、支持决策和改善知识传播,有望改变乳制品科学。然而,如果没有适当的系统设计,法学硕士可能会对特定领域的问题产生不相关或事实上不准确的回答。此外,大多数现有的法学硕士和相关工具都不是针对乳制品领域的需求量身定制的,限制了它们在该领域的实际应用。为了证明在乳品科学中采用法学硕士的可行性和实用价值,我们开发了一个由两部分组成的代理系统:(1)基于《乳品科学杂志》(JDS)的决策支持聊天机器人,以获得科学支持的见解;(2)用于与学术模型交互和可视化预测结果的自然语言界面。所有公开可用的JDS摘要和相关元数据都可以追溯到1917年,使用PubMed应用程序编程接口进行编译,形成一个科学知识库,使聊天机器人能够回答用户的问题。采用了检索增强生成框架,以确保LLaMA (Meta开发的法学硕士)生成的回答充分基于同行评议的文献,并在每个答案旁边引用了5个最相关的来源。为了解决JDS文献范围之外的问题,系统中加入了一个web搜索代理,以便从外部在线资源检索补充信息。由Databricks Research Transformer X (DBRX,由Databricks开发的法学硕士)提供支持的分级代理被用于评估法学硕士生成内容的可信度和相关性,以降低错误信息或幻觉反应的风险。该系统的第二个组成部分促进了与MilkBot的自然语言交互,MilkBot是一个已发布的贝叶斯产奶量预测模型。在用户以简单的语言提交问题后,系统将问题转换为MilkBot的模型参数,执行模型预测,并使用预测输出生成可视化。这项工作证明了LLM的能力,作为直观的,用户友好的界面,乳品特定的模型。据我们所知,这是第一个集成了来自科学文献、网络资源和学术模型的大规模信息以及自我评估能力的聊天机器人原型,可以为学者、顾问和农民提供特定于乳制品的见解。然而,实现法学硕士辅助决策的全部价值仍然存在挑战,例如缺乏针对特定区域的数据来根据当地情况定制答案,需要更强大的措施来保护数据安全和隐私,以及需要集成其他功能以实现更全面的决策支持。
Agents are all you need: Pioneering the use of agentic artificial intelligence to embrace large language models into dairy science.
Large language models (LLM) hold significant promise to transform dairy science by enhancing research interpretation, supporting decision making, and improving knowledge dissemination. However, without proper systematic design, LLM may generate irrelevant or factually inaccurate responses for domain-specific questions. Moreover, most existing LLM and related tools are not tailored to the needs of the dairy domain, limiting their practical application within the field. To demonstrate the feasibility and practical value of embracing LLM in dairy science, we developed a 2-component agentic system: (1) a decision-support chatbot grounded in the Journal of Dairy Science (JDS) for science-backed insights and (2) a natural language interface for interacting with academic models and visualizing prediction results. All publicly available JDS abstracts and associated metadata dating back to 1917 were compiled using the PubMed application programming interface, forming a scientific knowledge base that enables the chatbot to answer user questions. A retrieval-augmented generation framework was implemented to ensure that responses generated by LLaMA (a LLM developed by Meta) were well-grounded in peer-reviewed literature, with the 5 most relevant sources cited alongside each answer. To address questions beyond the coverage of JDS literature, a web search agent was incorporated into the system to retrieve supplementary information from external online sources. Grading agents, powered by Databricks Research Transformer X (DBRX; a LLM developed by Databricks), were incorporated to evaluate the credibility and relevance of LLM-generated content to mitigate the risk of misinformation or hallucinated responses. The second component of the system facilitates natural language interaction with MilkBot, a published Bayesian milk yield prediction model. After users submit questions in plain language, the system converts the question into model parameters for MilkBot, executes the model prediction, and uses the predicted output to generate visualizations. This work demonstrates the capability of LLM to serve as intuitive, user-friendly interfaces for dairy-specific models. To our knowledge, this is the first chatbot prototype that integrates large-scale information from scientific literature, web-based resources, and academic models, along with self-evaluation capability, to provide dairy-specific insights to scholars, consultants, and farmers. However, challenges remain to realize the full value of LLM-assisted decision making, such as the lack of region-specific data to tailor the answers to the local circumstances, the need for more robust measures to protect data security and privacy, and the need to integrate additional functions to enable more comprehensive decision support.
期刊介绍:
The official journal of the American Dairy Science Association®, Journal of Dairy Science® (JDS) is the leading peer-reviewed general dairy research journal in the world. JDS readers represent education, industry, and government agencies in more than 70 countries with interests in biochemistry, breeding, economics, engineering, environment, food science, genetics, microbiology, nutrition, pathology, physiology, processing, public health, quality assurance, and sanitation.