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

arXiv: https://arxiv.org/abs/2508.12393 · HTML: https://mlsanity.com/paper/2508.12393/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 45 of its 91 references that are in the map.
- First posted on arXiv 17 Aug 2025.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 30 of 45)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing](https://mlsanity.com/paper/2007.15779/) (2020)
- [Knowledge Graphs](https://mlsanity.com/paper/2003.02320/) (2020)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Benchmarking Retrieval-Augmented Generation for Medicine](https://mlsanity.com/paper/2402.13178/) (2024)
- [From System 1 to System 2: A Survey of Reasoning Large Language Models](https://mlsanity.com/paper/2502.17419/) (2025)
- [LightRAG: Simple and Fast Retrieval-Augmented Generation](https://mlsanity.com/paper/2410.05779/) (2024)
- [Confidence Improves Self-Consistency in LLMs](https://mlsanity.com/paper/2502.06233/) (2025)
- [Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme](https://mlsanity.com/paper/1706.05075/) (2017)
- [LLMs for Knowledge Graph Construction and Reasoning: Recent Capabilities and Future Opportunities](https://mlsanity.com/paper/2305.13168/) (2023)
- [MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models](https://mlsanity.com/paper/2308.09729/) (2023)
- [Extract, Define, Canonicalize: An LLM-based Framework for Knowledge Graph Construction](https://mlsanity.com/paper/2404.03868/) (2024)
- [DALK: Dynamic Co-Augmentation of LLMs and KG to answer Alzheimer's Disease Questions with Scientific Literature](https://mlsanity.com/paper/2405.04819/) (2024)
- [PiVe: Prompting with Iterative Verification Improving Graph-based Generative Capability of LLMs](https://mlsanity.com/paper/2305.12392/) (2023)
- [How Easily do Irrelevant Inputs Skew the Responses of Large Language Models?](https://mlsanity.com/paper/2404.03302/) (2024)
- [From human experts to machines: An LLM supported approach to ontology and knowledge graph construction](https://mlsanity.com/paper/2403.08345/) (2024)
- [SAC-KG: Exploiting Large Language Models as Skilled Automatic Constructors for Domain Knowledge Graphs](https://mlsanity.com/paper/2410.02811/) (2024)
- [PubTator 3.0: an AI-powered Literature Resource for Unlocking Biomedical Knowledge](https://mlsanity.com/paper/2401.11048/) (2024)
- [KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA](https://mlsanity.com/paper/2410.04660/) (2024)
- [Guiding Clinical Reasoning with Large Language Models via Knowledge Seeds](https://mlsanity.com/paper/2403.06609/) (2024)
- [PubMed and Beyond: Biomedical Literature Search in the Age of Artificial Intelligence](https://mlsanity.com/paper/2307.09683/) (2023)
- [Automated Construction of Theme-specific Knowledge Graphs](https://mlsanity.com/paper/2404.19146/) (2024)
- [Probabilistic Medical Predictions of Large Language Models](https://mlsanity.com/paper/2408.11316/) (2024)
- [UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction](https://mlsanity.com/paper/2402.06861/) (2024)
- [Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model](https://mlsanity.com/paper/2404.03080/) (2024)
- [Natural Language Processing for Information Extraction](https://mlsanity.com/paper/1807.02383/) (2018)

## Built on by (most cited first, 5 of 5)

- [AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction](https://mlsanity.com/paper/2604.16950/) (2026)
- [Closing Reasoning Gaps in Clinical Agents with Differential Reasoning Learning](https://mlsanity.com/paper/2602.09945/) (2026)
- [ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning](https://mlsanity.com/paper/2605.22734/) (2026)
- [Debate-on-Graph: Reliable and Adaptive Reasoning of Large Language Model on Uncertain Knowledge Graph](https://mlsanity.com/paper/2607.17266/) (2026)
- [When More Evidence Hurts: Publication-Bias Drift and Principled Stopping for Biomedical Causal Search](https://mlsanity.com/paper/2609.24101/) (2026)

## Abstract (arXiv)

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.