Conference paper · 2025

LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research

Shuo Yan, Ruochen Li, Ziming Luo, Zimu Wang, Daoyang Li, Liqiang Jing, Kaiyu He, Peilin Wu, Juntong Ni, George Michalopoulos, Yue Zhang, Ziyang Zhang, Mian Zhang, Zhiyu Chen, Xinya Du

BibTeX Copy

@inproceedings{yan2025lmrbench,
	address = {Suzhou, China},
	title = {{LMR}-{BENCH}: {Evaluating} {LLM} {Agent}'s {Ability} on {Reproducing} {Language} {Modeling} {Research}},
	url = {https://aclanthology.org/2025.emnlp-main.314/},
	doi = {10.18653/v1/2025.emnlp-main.314},
	booktitle = {Proceedings of the 2025 {Conference} on {Empirical} {Methods} in {Natural} {Language} {Processing}},
	publisher = {Association for Computational Linguistics},
	author = {Yan, Shuo and Li, Ruochen and Luo, Ziming and Wang, Zimu and Li, Daoyang and Jing, Liqiang and He, Kaiyu and Wu, Peilin and Ni, Juntong and Michalopoulos, George and Zhang, Yue and Zhang, Ziyang and Zhang, Mian and Chen, Zhiyu and Du, Xinya},
	year = {2025},
	keywords = {replichai},
	pages = {6164--6186},
}