Salvato in:
Dettagli Bibliografici
Autori principali: Yan, Shuo, Li, Ruochen, Luo, Ziming, Wang, Zimu, Li, Daoyang, Jing, Liqiang, He, Kaiyu, Wu, Peilin, Michalopoulos, George, Zhang, Yue, Zhang, Ziyang, Zhang, Mian, Chen, Zhiyu, Du, Xinya
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.17335
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912443112882176
author Yan, Shuo
Li, Ruochen
Luo, Ziming
Wang, Zimu
Li, Daoyang
Jing, Liqiang
He, Kaiyu
Wu, Peilin
Michalopoulos, George
Zhang, Yue
Zhang, Ziyang
Zhang, Mian
Chen, Zhiyu
Du, Xinya
author_facet Yan, Shuo
Li, Ruochen
Luo, Ziming
Wang, Zimu
Li, Daoyang
Jing, Liqiang
He, Kaiyu
Wu, Peilin
Michalopoulos, George
Zhang, Yue
Zhang, Ziyang
Zhang, Mian
Chen, Zhiyu
Du, Xinya
contents Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery. However, their capability in the fundamental yet crucial task of reproducing code from research papers, especially in the NLP domain, remains underexplored. This task includes unique complex reasoning challenges in the intellectual synthesis of abstract concepts and the comprehension of code repositories with interdependent files. Motivated by this gap, we present LMR-BENCH, a benchmark designed to systematically evaluate the capability of LLM agents on code reproduction from Language Modeling Research. It consists of 28 code reproduction tasks derived from 23 research papers published in top-tier NLP venues over the past five years, spanning nine fundamental categories. Models are provided with a research paper, a code repository containing one or more masked functions, and instructions for implementing these functions. We conduct extensive experiments in standard prompting and LLM agent settings with state-of-the-art LLMs, evaluating the accuracy of unit tests and performing LLM-based evaluation of code correctness. Experimental results reveal that even the most advanced models still exhibit persistent limitations in scientific reasoning and code synthesis, highlighting critical gaps in LLM agents' ability to autonomously reproduce scientific research
format Preprint
id arxiv_https___arxiv_org_abs_2506_17335
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
Yan, Shuo
Li, Ruochen
Luo, Ziming
Wang, Zimu
Li, Daoyang
Jing, Liqiang
He, Kaiyu
Wu, Peilin
Michalopoulos, George
Zhang, Yue
Zhang, Ziyang
Zhang, Mian
Chen, Zhiyu
Du, Xinya
Software Engineering
Artificial Intelligence
Large language model (LLM) agents have demonstrated remarkable potential in advancing scientific discovery. However, their capability in the fundamental yet crucial task of reproducing code from research papers, especially in the NLP domain, remains underexplored. This task includes unique complex reasoning challenges in the intellectual synthesis of abstract concepts and the comprehension of code repositories with interdependent files. Motivated by this gap, we present LMR-BENCH, a benchmark designed to systematically evaluate the capability of LLM agents on code reproduction from Language Modeling Research. It consists of 28 code reproduction tasks derived from 23 research papers published in top-tier NLP venues over the past five years, spanning nine fundamental categories. Models are provided with a research paper, a code repository containing one or more masked functions, and instructions for implementing these functions. We conduct extensive experiments in standard prompting and LLM agent settings with state-of-the-art LLMs, evaluating the accuracy of unit tests and performing LLM-based evaluation of code correctness. Experimental results reveal that even the most advanced models still exhibit persistent limitations in scientific reasoning and code synthesis, highlighting critical gaps in LLM agents' ability to autonomously reproduce scientific research
title LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research
topic Software Engineering
Artificial Intelligence
url https://arxiv.org/abs/2506.17335