Preprint · 2026

What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations

Yujie Luo, Zhuoyun Yu, Xuehai Wang, Yuqi Zhu, Ningyu Zhang, Lanning Wei, Lun Du, Da Zheng, Huajun Chen

Abstract

Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of retrieval-augmented generation (RAG) methods, which fail to capture latent technical details hidden in referenced papers. Furthermore, previous approaches tend to overlook valuable implementation-level code signals and lack structured knowledge representations that support multi-granular retrieval and reuse. To overcome these challenges, we propose Executable Knowledge Graphs (xKG), a pluggable, paper-centric knowledge base that automatically integrates code snippets and technical insights extracted from scientific literature. When integrated into three agent frameworks with two different LLMs, xKG shows substantial performance gains (10.9% with o3-mini) on PaperBench, demonstrating its effectiveness as a general and extensible solution for automated AI research replication. Code is available at https://github.com/zjunlp/xKG.

BibTeX Copy

@misc{luo_what_2026,
	title = {What {Makes} {AI} {Research} {Replicable}? {Executable} {Knowledge} {Graphs} as {Scientific} {Knowledge} {Representations}},
	shorttitle = {What {Makes} {AI} {Research} {Replicable}?},
	url = {http://arxiv.org/abs/2510.17795},
	doi = {10.48550/arXiv.2510.17795},
	abstract = {Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the limitations of retrieval-augmented generation (RAG) methods, which fail to capture latent technical details hidden in referenced papers. Furthermore, previous approaches tend to overlook valuable implementation-level code signals and lack structured knowledge representations that support multi-granular retrieval and reuse. To overcome these challenges, we propose Executable Knowledge Graphs (xKG), a pluggable, paper-centric knowledge base that automatically integrates code snippets and technical insights extracted from scientific literature. When integrated into three agent frameworks with two different LLMs, xKG shows substantial performance gains (10.9\% with o3-mini) on PaperBench, demonstrating its effectiveness as a general and extensible solution for automated AI research replication. Code is available at https://github.com/zjunlp/xKG.},
	urldate = {2026-11-05},
	publisher = {arXiv},
	author = {Luo, Yujie and Yu, Zhuoyun and Wang, Xuehai and Zhu, Yuqi and Zhang, Ningyu and Wei, Lanning and Du, Lun and Zheng, Da and Chen, Huajun},
	month = apr,
	year = {2026},
	note = {arXiv:2510.17795 [cs.CL]},
	keywords = {Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Machine Learning, Computer Science - Multiagent Systems, Computer Science - Software Engineering},
}