Empowering AI data scientists using a multi-agent LLM framework with self-evolving capabilities for autonomous, tool-aware biomedical data analyses. Bu, D., Sun, J., Li, K., He, Z., Huang, W., Hu, J., Zhang, S., Lei, S., Huo, P., Wang, Z., Wang, S., Wang, T., Gao, K., Wu, Y., Zhao, L., Wang, K., Li, G., Song, H., Jin, Y., Zhang, K., Chen, R., & Zhao, Y. Nature Biomedical Engineering, Nature Publishing Group, March, 2026.
Empowering AI data scientists using a multi-agent LLM framework with self-evolving capabilities for autonomous, tool-aware biomedical data analyses [link]Paper  doi  abstract   bibtex   
Artificial intelligence agents are emerging as powerful applications of large language models (LLMs), automating complex tasks and enabling scientific data exploration. However, their use in biomedical data analysis remains limited by the difficulty of handling specialized tools and multistep reasoning. Here we introduce BioMedAgent, a self-evolving LLM multi-agent framework, which learns to use diverse bioinformatics tools and chain them into executable workflows through interactive exploration and memory retrieval algorithms. It allows biomedical users to initiate tasks using natural language, without requiring computational expertise. Evaluated on our newly released BioMed-AQA benchmark comprising 327 biomedical data tasks, BioMedAgent achieved a 77% success rate, surpassing other LLM agents, and generalized robustly to the external BixBench dataset. Beyond benchmarks, it autonomously performs cross-omics analysis, machine-learning modelling and pathology image segmentation, highlighting its potential to advance biomedical research and extend to other scientific domains requiring complex tool integration and multistep reasoning.
@article{bu_empowering_2026,
	title = {Empowering {AI} data scientists using a multi-agent {LLM} framework with self-evolving capabilities for autonomous, tool-aware biomedical data analyses},
	copyright = {2026 The Author(s), under exclusive licence to Springer Nature Limited},
	issn = {2157-846X},
	url = {https://www.nature.com/articles/s41551-026-01634-6},
	doi = {10.1038/s41551-026-01634-6},
	abstract = {Artificial intelligence agents are emerging as powerful applications of large language models (LLMs), automating complex tasks and enabling scientific data exploration. However, their use in biomedical data analysis remains limited by the difficulty of handling specialized tools and multistep reasoning. Here we introduce BioMedAgent, a self-evolving LLM multi-agent framework, which learns to use diverse bioinformatics tools and chain them into executable workflows through interactive exploration and memory retrieval algorithms. It allows biomedical users to initiate tasks using natural language, without requiring computational expertise. Evaluated on our newly released BioMed-AQA benchmark comprising 327 biomedical data tasks, BioMedAgent achieved a 77\% success rate, surpassing other LLM agents, and generalized robustly to the external BixBench dataset. Beyond benchmarks, it autonomously performs cross-omics analysis, machine-learning modelling and pathology image segmentation, highlighting its potential to advance biomedical research and extend to other scientific domains requiring complex tool integration and multistep reasoning.},
	language = {en},
	urldate = {2026-03-31},
	journal = {Nature Biomedical Engineering},
	publisher = {Nature Publishing Group},
	author = {Bu, Dechao and Sun, Jingbo and Li, Kun and He, Zihao and Huang, Wei and Hu, Jinlin and Zhang, Shanshan and Lei, Shuangshuang and Huo, Peipei and Wang, Zhihao and Wang, Sheng and Wang, Tao and Gao, Kai and Wu, Yang and Zhao, Lianhe and Wang, Kai and Li, Gen and Song, Huan and Jin, Yang and Zhang, Kang and Chen, Runsheng and Zhao, Yi},
	month = mar,
	year = {2026},
	keywords = {Biomedical engineering, Computational biology and bioinformatics, Medical research, Software},
	pages = {1--16},
}
Downloads: 0
About
Documentation
Keywords
Search
Users
Terms and Conditions of Use
Privacy Policy
Sitemap
© BibBase.org 2021