Large Language Model Agents for Biomedicine: A Comprehensive Review of Methods, Evaluations, Challenges, and Future Directions
Open accessAbstract
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.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Underrepresented populations and rare diseases are frequently sparsely documented, creating blind spots that may lead to unsafe generalization when systems are deployed across heterogeneous clinical environments.
“Underrepresented populations and rare diseases are frequently sparsely documented, creating blind spots that may lead to unsafe generalization when systems are deployed across heterogeneous clinical environments [49].”
From The next paradigm in bioinformatics: a review of multi-agent systems and foundational models for end-to-end scientific discovery (2026) · cites this paper as [49]
Cites
ChatGPT outperforms crowd workers for text-annotation tasks
Gilardi, F., Alizadeh, M., & Kubli, M. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2305016120 · Cited by 1,197 · see citing works
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
Li, C., Wong, C., Zhang, S., Usuyama, N., Liu, H., Yang, J., Naumann, T., Poon, H., & Gao, J. (2023) · arXiv · doi:10.48550/arxiv.2306.00890 · Cited by 590 · cited 1× · see citing works
“Representative systems including LLaVA-Med [52] and GeneVerse [53] enable agents to interpret imaging and genetic data through joint embedding and instruction-following capabilities.”
Towards conversational diagnostic artificial intelligence
Tu, T., Schaekermann, M., Palepu, A., Saab, K., Freyberg, J., Tanno, R., Wang, A., Li, B., Amin, M., Cheng, Y., et al. (2025) · Nature · doi:10.1038/s41586-025-08866-7 · Cited by 366 · cited 1× · see citing works
“The development of these specialized, interactive benchmarks is an important trend in evaluating biomedical LLM agents [72].”
Multimodal Large Language Models in Health Care: Applications, Challenges, and Future Outlook.
AlSaad, R., Abd-alrazaq, A., Boughorbel, S., Ahmed, A., Renault, M.-A., Damseh, R., & Sheikh, J. (2024) · Journal of medical Internet research · doi:10.2196/59505 · Cited by 349 · cited 2× · see citing works
“Agents must also handle missing data gracefully, which calls for models explicitly designed for partial or sparse input [81].”
Empowering biomedical discovery with AI agents
Gao, S., Fang, A., Huang, Y., Giunchiglia, V., Noori, A., Schwarz, J. R., Ektefaie, Y., Kondic, J., & Zitnik, M. (2024) · Cell · doi:10.1016/j.cell.2024.09.022 · Cited by 315 · see citing works
Palaniappan, K., Lin, E. Y. T., & Vogel, S. (2024) · Healthcare · doi:10.3390/healthcare12050562 · Cited by 301 · see citing works
Liu, S., McCoy, A. B., & Wright, A. (2025) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaf008 · Cited by 200 · cited 4× · see citing works
“Prompt engineering and structured integration of retrieved content are also critical to ensure coherence and factual alignment during response synthesis [42].”
InfluentialMedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning
Tang, X., Zou, A., Zhang, Z., Li, Z., Zhao, Y., Zhang, X., Cohan, A., & Gerstein, M. (2024) · Findings of the Association for Computational Linguistics ACL 2024 · doi:10.18653/v1/2024.findings-acl.33 · Cited by 133 · see citing works
Biomni: A general-purpose biomedical ai agent
Huang, K., Zhang, S., Wang, H., Qu, Y., Lu, Y., Roohani, Y., Li, R., Qiu, L., Li, G., Zhang, J., et al. (2025) · doi:10.1101/2025.05.30.656746 · Cited by 125 · see citing works
Enhancing diagnostic capability with multi-agents conversational large language models
Chen, X., Yi, H., You, M., Liu, W., Wang, L., Li, H., Zhang, X., Guo, Y., Fan, L., Chen, G., et al. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01550-0 · Cited by 117 · see citing works
An automated framework for assessing how well LLMs cite relevant medical references
Wu, K., Wu, E., Wei, K., Zhang, A., Casasola, A., Nguyen, T., Riantawan, S., Shi, P., Ho, D., & Zou, J. (2025) · Nature Communications · doi:10.1038/s41467-025-58551-6 · Cited by 72 · cited 6× · see citing works
“For instance, SourceCheckup employs RAG to trace whether LLM-generated statements are supported by citations, enabling citation-level fact-checking in medical QA systems [5].”
InfluentialRethinking clinical trials for medical AI with dynamic deployments of adaptive systems
Rosenthal, J. T., Beecy, A., & Sabuncu, M. R. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01674-3 · Cited by 59 · see citing works
The Virtual Lab: AI Agents Design New SARS-CoV-2 Nanobodies with Experimental Validation
Swanson, K., Wu, W., Bulaong, N. L., Pak, J. E., & Zou, J. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.11.11.623004 · Cited by 56 · see citing works
Shi, W., Xu, R., Zhuang, Y., Yu, Y., Zhang, J., Wu, H., Zhu, Y., Ho, J. C., Yang, C., & Wang, M. D. (2024) · Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2024.emnlp-main.1245 · Cited by 54 · cited 1× · see citing works
“…biomedical agents employ tool calling in tasks such as literature and gene retrieval via PubMed or NCBI APIs [4,26], chemical structure analysis via cheminformatics packages [20], and automated experimentation through lab interface protocols, or interaction with structured EHR databases [49].”
MMedAgent: Learning to Use Medical Tools with Multi-modal Agent
Li, B., Yan, T., Pan, Y., Luo, J., Ji, R., Ding, J., Xu, Z., Liu, S., Dong, H., Lin, Z., et al. (2024) · Findings of the Association for Computational Linguistics: EMNLP 2024 · doi:10.18653/v1/2024.findings-emnlp.510 · Cited by 54 · see citing works
From Intention To Implementation: Automating Biomedical Research via LLMs
Luo, Y., Shi, L., Li, Y., Zhuang, A., Gong, Y., Liu, L., & Lin, C. (2024) · arXiv · doi:10.48550/arxiv.2412.09429 · Cited by 53
Comeau, D. S., Bitterman, D. S., & Celi, L. A. (2025) · npj Digital Medicine · doi:10.1038/s41746-025-01443-2 · Cited by 44 · cited 3× · see citing works
“Purpose-built metrics like hallucination rates [67], demographic bias scores [79], citation integrity [5], and reasoning traceability [28] are essential complements to traditional evaluation.”
Liu, L., Yang, X., Lei, J., Shen, Y., Wang, J., Wei, P., Chu, Z., Qin, Z., & Ren, K. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3709941 · Cited by 31 · see citing works
Sankar, B. S., Gilliland, D., Rincon, J., Hermjakob, H., Yan, Y., Adam, I., Lemaster, G., Wang, D., Watson, K., Bui, A., et al. (2024) · Bioengineering · doi:10.3390/bioengineering11100984 · Cited by 26 · see citing works
CoD, towards an interpretable medical agent using chain of diagnosis
Chen, J., Gui, C., Gao, A., Ji, K., Wang, X., Wan, X., & Wang, B. (2025) · Findings of the Association for Computational Linguistics: ACL 2025 · doi:10.18653/v1/2025.findings-acl.740 · Cited by 13 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Branda, F., Ahmed, M. M., Ciccozzi, M., Guzzi, P. H., & Scarpa, F. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag245 · Cited by 2 · see citing works
- Authors
- Xu, X., & Sankar, R.
- Affiliations
- University of South Florida (US)
- Venue
- Information
- Publisher
- MDPI AG
- Published
- 2025-10-14
- Volume
- 16
- Issue
- 10
- Pages
- 894
- ISSN
- 2078-2489 (ISSN-L)
- OpenAlex
- W4415280829
- Cited by
- 20
- References
- 20
- Citations by year
- 2026: 18 · 2025: 2
- FWCI
- 4.81
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Information (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Biomedical Text Mining and Ontologies
- Keywords
- LLM agents, clinical decision support, patient simulation, hallucination mitigation, interpretability, tool reliability, data bias, regulatory challenges, continual learning, federated learning, multi-agent coordination, human-AI collaboration, multimodal benchmark
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
