Meihao Fan

Meihao Fan

Phd Student at RUC

Meihao Fan

This is Meihao Fan’s personal homepage.

A short introduction

I am Meihao Fan (范梅浩 in Chinese), currently a Ph.D. student in Computer Science at Renmin University of China (RUC). I am a member of DEKE Lab of Renmin University of China and under the supervision of Prof. Ju Fan and Prof. Xiaoyong Du. Before that, I completed my B.S. in 2023 at Chongqing Jiaotong University.

My research focuses on LLM-powered data agents, reinforcement learning, and post-training for open-source LLMs. I am interested in building cost-effective and reliable agentic systems for data-intensive tasks such as data preparation, entity resolution, and autonomous data science.

Selected Publications

  • Meihao Fan, Ju Fan, Yuxin Zhang, Shaolei Zhang, Xiaoyong Du, Jie Song, Peng Li, Fuxin Jiang, Tieying Zhang, Jianjun Chen: DeepPrep: An LLM-Powered Agentic System for Autonomous Data Preparation. VLDB 2026 (Under Review). [paper] [slides]
  • Chao Deng, Ju Fan, Yuyu Luo, Qinliang Xue, Meihao Fan, Yuxin Zhang, Min Zhang, Xiaofeng Jia, Jing Zhang, Xiaoyong Du: TACO: A Benchmark for Open-Domain Text-to-SQL with Ambiguous and Cross-Database Queries. VLDB 2026 (Accepted). [paper] [slides]
  • Anonymous Authors (incl. Meihao Fan): DeepAnalyze: Agentic Large Language Models for Autonomous Data Science. ICML 2026 (Under Review). [paper] [slides]
  • Anonymous Authors (incl. Meihao Fan): CODA-BENCH: Can Code Agents Handle Data-Intensive Tasks? ICML 2026 (Under Review). [paper] [slides]
  • Yuxin Zhang, Meihao Fan, Ju Fan, Mingyang Yi, Yuyu Luo, Jian Tan, Guoliang Li: Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards. SIGMOD 2026 (Accepted). [paper] [slides]
  • Meihao Fan, Ju Fan, Nan Tang, Lei Cao, Guoliang Li, Xiaoyong Du: AutoPrep: Natural Language Question-Aware Data Preparation with a Multi-Agent Framework. VLDB 2025 (Accepted). [paper] [slides]
  • Meihao Fan, Xiaoyue Han, Ju Fan, Chengliang Chai, Nan Tang, Guoliang Li, Xiaoyong Du: Cost-Effective In-Context Learning for Entity Resolution: A Design Space Exploration. ICDE 2024 (Accepted). [paper] [slides]

Experience

  • ByteDance - Research Intern (LLM Data Agent Systems) March 2025 - March 2026
  • Renmin University of China - Research Assistant Sept 2023 - Present

Selected Awards

  • National Scholarship (Ph.D.), Ministry of Education, China, 2025 (The only 2nd-year Ph.D. recipient in the college)
  • National Scholarship (B.S.), Ministry of Education, China, 2023 (The only recipient in the college)
  • Mingde Scholarship Nomination Award, Chongqing Jiaotong University, 2023 (Top 20 in the university)