LLMs and AI Agents in Biomedical and Health Sciences

Dear Colleagues,

Recent advances in large language models (LLMs) and AI agents are transforming the biomedical and health sciences by enabling systems that can reason, interact, and act across complex, data-rich environments. Unlike earlier task-specific machine learning models, LLMs and agentic AI systems can integrate heterogeneous biomedical data, perform multi-step reasoning, collaborate with humans, and dynamically adapt to evolving clinical and research contexts. These capabilities present unprecedented opportunities for advancing biomedical discovery, clinical decision support, digital health, education, and healthcare operations, while also raising critical challenges related to safety, reliability, interpretability, ethics, and governance. 

This Special Issue focuses on the design, evaluation, and application of LLMs and AI agents in biomedical and health sciences, emphasizing systems that move beyond static prediction toward interactive, goal-directed, and context-aware intelligence. The scope includes foundational methods, system architectures, and real-world deployments spanning clinical care, biomedical research, public health, and health system operations. Topics of interest include LLM-based clinical and scientific reasoning, multimodal and agentic AI systems, retrieval-augmented generation (RAG), tool-using and autonomous agents, human–AI collaboration, and methods for ensuring robustness, transparency, and trustworthiness in high-stakes biomedical settings. 

The purpose of this Special Issue is threefold. First, it aims to provide a dedicated venue for high-quality methodological and applied research on LLMs and AI agents tailored to biomedical and healthcare domains. Second, it seeks to establish best practices for evaluation, validation, and governance of these systems, particularly in safety-critical and ethically sensitive applications. Third, it encourages interdisciplinary contributions that bridge artificial intelligence, medicine, biomedical informatics, health systems engineering, and social sciences. 

This Special Issue complements and extends existing literature on medical AI and biomedical informatics by shifting the focus from isolated predictive models to agentic, interactive, and system-level AI. While prior work has largely emphasized supervised learning and narrow clinical tasks, this issue highlights emerging paradigms centered on reasoning, autonomy, multimodal integration, and continuous human–AI interaction. By bringing together theoretical advances, practical implementations, and real-world evaluations, this Special Issue aims to advance the responsible development and translation of LLMs and AI agents into biomedical research and healthcare practice.

Dr. Zhenhong Hu
Dr. Yingbo Ma
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. AI is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1800 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• large language models (LLMs)
• agents
• biomedical AI
• healthcare AI
• clinical decision support
• multimodal AI
• retrieval-augmented generation (RAG)
• agentic AI systems
• human–AI collaboration
• trustworthy and explainable AI