In this paper, we propose a novel system that integrates state-of-the-art, domain-specific large language models with advanced information retrieval techniques to deliver comprehensive and context-aware responses. Our approach facilitates seamless interaction among diverse components, enabling cross-validation of outputs to produce accurate, high-quality responses enriched with relevant data, images, tables, and other modalities. We demonstrate the system's capability to enhance response precision by leveraging a robust question-answering model, significantly improving the quality of dialogue generation. The system provides an accessible platform for real-time, high-fidelity interactions, allowing users to benefit from efficient human-computer interaction, precise retrieval, and simultaneous access to a wide range of literature and data. This dramatically improves the research efficiency of professionals in the biomedical and pharmaceutical domains and facilitates faster, more informed decision-making throughout the R\&D process. Furthermore, the system proposed in this paper is available atthis https URL.
View on arXiv@article{chen2025_2504.12341,
title={ Streamlining Biomedical Research with Specialized LLMs },
author={ Linqing Chen and Weilei Wang and Yubin Xia and Wentao Wu and Peng Xu and Zilong Bai and Jie Fang and Chaobo Xu and Ran Hu and Licong Xu and Haoran Hua and Jing Sun and Hanmeng Zhong and Jin Liu and Tian Qiu and Haowen Liu and Meng Hu and Xiuwen Li and Fei Gao and Yong Gu and Tao Shi and Chaochao Wang and Jianping Lu and Cheng Sun and Yixin Wang and Shengjie Yang and Yuancheng Li and Lu Jin and Lisha Zhang and Fu Bian and Zhongkai Ye and Lidong Pei and Changyang Tu },
journal={arXiv preprint arXiv:2504.12341},
year={ 2025 }
}