Cover Image

Saved in:
Bibliographic Details
Main 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.
Format: Preprint
Published: 2025
Subjects:
Computation and Language
Artificial Intelligence
Online Access:https://arxiv.org/abs/2510.06186
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • 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

Similar Items