ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows

By Penghao Wang, Yuhao Zhou, Mengxuan Wu, Ziheng Qin, Bangyuan Zhu, Sheng-Jun Huang, Xuan-Lei Zhao, Pan-Pan Zhang, Xiao-Jiang Peng, Yuzhang Shang and 5 more. 2025

Subfields: Large Language Models, LLM Agents & Tool Use, Evaluation & Benchmarks