Explore DARE-Bench, a 6,300-task benchmark for training LLM data science agents with verifiable rewards, improving accuracy, reliability and execution.
MAY 07, 2026|6 min read
Ruofan Wu
Ruofan Wu is a Ph.D. student in Computer Science at the University of Houston, advised by Prof. Feng Yan. Her research focuses on the end-to-end optimization of agentic AI systems, covering the full lifecycle from automated data synthesis to specialized training and multi-hop reasoning. Previously, she worked on large-scale distributed training and AI for Science. She received her bachelor's degree in Intelligent Medical Engineering from Northeastern University (China), where she also completed a comprehensive foundation in pre-clinical medicine, bringing a unique scientific perspective to her research.
