MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph

Abstract

The rapid expansion of medical literature challenges the scalable structuring of domain knowledge. Knowledge Graphs (KGs) offer a solution, yet current construction methods lack generalizability and ignore the temporal dynamics of evolving knowledge. To address this, we introduce MedKGent, a Large Language Model (LLM) agent framework for building temporally evolving medical KGs. Using over 10 million PubMed abstracts from 1975 to 2023, MedKGent incrementally constructs a KG daily via two specialized agents. The Extractor Agent identifies knowledge triples and assigns confidence scores, while the Constructor Agent integrates these triples into a temporal graph, reinforcing recurring knowledge and resolving conflicts. The resulting KG contains 156,275 entities and 2,971,384 triples, making it, to our knowledge, the largest LLM-derived medical KG to date. Automated and expert assessments showed triple-validity rates approaching 90%. In downstream evaluations, MedKGent-KG significantly improved retrieval-augmented generation for five LLMs across seven medical question-answering benchmarks. Together, these results position MedKGent as a scalable and temporally aware infrastructure for medical knowledge representation and literature-grounded AI research.

Contribution highlights

• To address this, we introduce MedKGent, a Large Language Model (LLM) agent framework for building temporally evolving medical KGs.

Extracted from the public abstract; no claims have been added.

Code and data

Publication metadata

DOI

10.1038/s41746-026-03058-7

Version relationship

• Preprint: https://arxiv.org/abs/2508.12393
• Version of record: https://doi.org/10.1038/s41746-026-03058-7

BibTeX

@article{Zhang2026Medkgentlarge,
  title = {MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph},
  author = {Duzhen Zhang and Zixiao Wang and Zhong-Zhi Li and Yahan Yu and Shuncheng Jia and Jiahua Dong and Haotian Xu and Xing Wu and Yingying Zhang and Tielin Zhang and Jie Yang and Xiuying Chen and Le Song},
  journal = {npj Digital Medicine},
  year = {2026},
  url = {https://arxiv.org/abs/2508.12393},
  doi = {10.1038/s41746-026-03058-7}
}