# ATOM: AdapTive and OptiMized dynamic temporal knowledge graph construction using LLMs

arXiv: https://arxiv.org/abs/2510.22590 · HTML: https://mlsanity.com/paper/2510.22590/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 26 Oct 2025.

## Builds on (most cited first, 17 of 17)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Zep: A Temporal Knowledge Graph Architecture for Agent Memory](https://mlsanity.com/paper/2501.13956/) (2025)
- [DocRED: A Large-Scale Document-Level Relation Extraction Dataset](https://mlsanity.com/paper/1906.06127/) (2019)
- [Large Language Models on Graphs: A Comprehensive Survey](https://mlsanity.com/paper/2312.02783/) (2023)
- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)
- [Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction](https://mlsanity.com/paper/2205.12696/) (2022)
- [A Survey on Temporal Knowledge Graph: Representation Learning and Applications](https://mlsanity.com/paper/2403.04782/) (2024)
- [LLM-empowered knowledge graph construction: A survey](https://mlsanity.com/paper/2510.20345/) (2025)
- [Question-Based Retrieval using Atomic Units for Enterprise RAG](https://mlsanity.com/paper/2405.12363/) (2024)
- [On the Evolution of Knowledge Graphs: A Survey and Perspective](https://mlsanity.com/paper/2310.04835/) (2023)
- [Scalable and Domain-General Abstractive Proposition Segmentation](https://mlsanity.com/paper/2406.19803/) (2024)
- [Retrieval Augmented Generation for Dynamic Graph Modeling](https://mlsanity.com/paper/2408.14523/) (2024)
- [Scientific Discovery by Machine Intelligence: A New Avenue for Drug Research](https://mlsanity.com/paper/1506.07116/) (2015)
- [Occams Razor for Big Data? On Detecting Quality in Large Unstructured Datasets](https://mlsanity.com/paper/2011.08663/) (2020)
- [Enhancing Knowledge Graph Construction: Evaluating with Emphasis on Hallucination, Omission, and Graph Similarity Metrics](https://mlsanity.com/paper/2502.05239/) (2025)

## Built on by (most cited first, 7 of 7)

- [SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges](https://mlsanity.com/paper/2606.15971/) (2026)
- [TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction](https://mlsanity.com/paper/2607.05001/) (2026)
- [AI Economist Agent: An Agentic Framework for Evidence-Based Economic and Financial Analysis with RAG, Knowledge Graphs, and Large Language Models](https://mlsanity.com/paper/2606.20041/) (2026)
- [From Static Bibliometrics to Dynamic Knowledge Graphs: An LLM-Powered Framework for Modernizing Science, Technology, and Innovation (STI) Analytics](https://mlsanity.com/paper/2607.21327/) (2026)
- [LLM-Assisted Ontology Engineering and Construction of a French Legal Knowledge Graph](https://mlsanity.com/paper/2607.24551/) (2026)
- [SAG: SQL-Retrieval Augmented Generation with Query-Time Dynamic Hyperedges](https://mlsanity.com/paper/2608.12129/) (2026)
- [C-Unseen: Weak Signal Detection in Dynamic Temporal Knowledge Graphs via LLM Reasoning](https://mlsanity.com/paper/2608.26870/) (2026)

## Abstract (arXiv)

In today's rapidly expanding data landscape, knowledge extraction from unstructured text is vital for real-time analytics, temporal inference, and dynamic memory frameworks. However, traditional static knowledge graph (KG) construction often overlooks the dynamic and time-sensitive nature of real-world data, limiting adaptability to continuous changes. Moreover, recent zero- or few-shot approaches that avoid domain-specific fine-tuning or reliance on prebuilt ontologies often suffer from instability across multiple runs, as well as incomplete coverage of key facts. To address these challenges, we introduce ATOM (AdapTive and OptiMized), a few-shot and scalable approach that builds and continuously updates Temporal Knowledge Graphs (TKGs) from unstructured texts. ATOM splits input documents into minimal, self-contained "atomic" facts, improving extraction exhaustivity and stability. Then, it constructs atomic TKGs from these facts, employing a dual-time modeling that distinguishes between when information is observed and when it is valid. The resulting atomic TKGs are subsequently merged in parallel. Empirical evaluations demonstrate that ATOM achieves ~18% higher exhaustivity, ~33% better stability, and over ~90% latency reduction compared to baseline methods, demonstrating a strong scalability potential for dynamic TKG construction.