Year: 2025
Type: preprint
Abstract: Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing works largely adopt one-shot settings, ignoring the iterative and feedback-driven nature of realistic workflows of scientific research development. To address this gap, we present RECODE-H, a benchmark of 102 tasks from research papers and repositories that evaluates LLM agents through multi-turn interactions with LLM-simulated human feedback. It includes structured instructions,unit tests, and a five-level feedback hierarchy to reflect realistic researcher-agent collaboration. We further present ReCodeAgent, a framework that integrates feedback into iterative code generation. Experiments with leading LLMs, including GPT-5, Claude-Sonnet-4, DeepSeek-V3.1, and Gemini 2.5, show substantial performance gains with richer feedback, while also highlighting ongoing challenges in the generation of complex research code. RECODE-H establishes a foundation for developing adaptive, feedback-driven LLM agents in scientific research implementation
Source: arXiv (Cornell University)
Authors: Miao, Chunyu, Zou, Henry Peng, Li, Yangning, Chen, Yankai, Wang, Yibo, Wang, Fangxin, Li, Yifan, Yang, Wooseong, He, Bowei, Zhang, Xinni, Yu, Dianzhi, Yang, Hanchen, Nguyen, Hoang H, Zhou, Yue, Yang, Jie, Guo, Jizhou, Fan, Wenzhe, Yeh, Chin-Yuan, Meng, Panpan, Fang, Liancheng, Qi, Jinhu, Huang, Wei-Chieh, Gu, Zhengyao, Han, Yuwei, He, Langzhou, Yang, Yuyao, Li, Yinghui, Zheng, Hai-Tao, Liu, Xue, King, Irwin, Yu, Philip S.
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414981968
Cites:
Cited by:
Related to: