Large Language Model Agents for Biomedicine: A Comprehensive Review of Methods, Evaluations, Challenges, and Future Directions
Open Access
- 14 October 2025
- journal article
- review article
- Published by MDPI AG in Information
- Vol. 16 (10) , 894
Abstract
Large language model (LLM)-based agents are rapidly emerging as transformative tools across biomedical research and clinical applications. By integrating reasoning, planning, memory, and tool use capabilities, these agents go beyond static language models to operate autonomously or collaboratively within complex healthcare settings. This review provides a comprehensive survey of biomedical LLM agents, spanning their core system architectures, enabling methodologies, and real-world use cases such as clinical decision making, biomedical research automation, and patient simulation. We further examine emerging benchmarks designed to evaluate agent performance under dynamic, interactive, and multimodal conditions. In addition, we systematically analyze key challenges, including hallucinations, interpretability, tool reliability, data bias, and regulatory gaps, and discuss corresponding mitigation strategies. Finally, we outline future directions in areas such as continual learning, federated adaptation, robust multi-agent coordination, and human AI collaboration. This review aims to establish a foundational understanding of biomedical LLM agents and provide a forward-looking roadmap for building trustworthy, reliable, and clinically deployable intelligent systems.Keywords
All Related Versions
This publication has 83 references indexed in Scilit:
- From intention to implementation: automating biomedical research via LLMsScience China Information Sciences, 2025
- A “True Lifecycle Approach” towards governing healthcare AI with the GCC as a global governance modelnpj Digital Medicine, 2025
- Rethinking clinical trials for medical AI with dynamic deployments of adaptive systemsnpj Digital Medicine, 2025
- An automated framework for assessing how well LLMs cite relevant medical referencesNature Communications, 2025
- Towards conversational diagnostic artificial intelligenceNature, 2025
- Large language model agents can use tools to perform clinical calculationsnpj Digital Medicine, 2025
- Preventing unrestricted and unmonitored AI experimentation in healthcare through transparency and accountabilitynpj Digital Medicine, 2025
- Empowering biomedical discovery with AI agentsCell, 2024
- Evaluating large language models as agents in the clinicnpj Digital Medicine, 2024
- GIT-Mol: A multi-modal large language model for molecular science with graph, image, and textComputers in Biology and Medicine, 2024