👋 Hi there, I’m Pengfei Wang

🚀 About Me

NLP Engineer · AI Researcher

• 🌱 Currently, I focus on Text-to-SQL, Agentic RL, and AI Agents.
• 🎓 I received my master's degree from Zhejiang University under the supervision of Prof. Yunjun Gao.
• 📧 [email protected]
• 🔗 Google Scholar

---

📰 News

• 2025.09: 🏆 We have achieved #1 Rank on the challenging Text-to-SQL leaderboard BIRD leaderboard with 81.67% execution accuracy!

---

💼 Work Experience

Period	Position & Company
2024.04–now	Senior Algorithm Engineer @ Ant Digital Technologies, Ant Group
2023.05–2023.08	Summer Algorithm Intern @ Seed (formerly AI-Lab-NLP), ByteDance

---

📚 Selected Research

• Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scaling
  Pengfei Wang, Baolin Sun, Xuemei Dong, Yaxun Dai, Hongwei Yuan, Mengdie Chu, Yingqi Gao, Xiang Qi, Peng Zhang, Ying Yan
  Technical Report | Paper | Code

• PromptEM: Prompt-tuning for Low-resource Generalized Entity Matching
  Pengfei Wang, Xiaocan Zeng, Lu Chen, Fan Ye, Yuren Mao, Junhao Zhu, Yunjun Gao
  VLDB 2023 | Paper | Code

• Towards Explainable Table Interpretation Using Multi-view Explanations
  Yunjun Gao, Pengfei Wang, Xiaocan Zeng, Lu Chen, Yuren Mao, Ziheng Wei, Miao Li
  ICDE 2023 | Paper | Code

• CollaborEM: A Self-supervised Entity Matching Framework Using Multi-features Collaboration
  Congcong Ge, Pengfei Wang, Lu Chen, Xiaoze Liu, Baihua Zheng, Yunjun Gao
  TKDE | Paper | Code

• MultiEM: Efficient and Effective Unsupervised Multi-Table Entity Matching
  Xiaocan Zeng, Pengfei Wang, Yuren Mao, Lu Chen, Xiaoze Liu, Yunjun Gao
  ICDE 2024 | Paper | Code

• ClusterEA: Scalable Entity Alignment with Stochastic Training and Normalized Mini-batch Similarities
  Yunjun Gao, Xiaoze Liu, Junyang Wu, Tianyi Li, Pengfei Wang, Lu Chen
  KDD 2022 | Paper

• UniView: A Unified Autonomous Materialized View Management System for Various Databases
  Zhenrong Xu, Pengfei Wang, Guoze Xue, Qitong Yan, Shenghao Gong, Yelan Jiang, Yuren Mao, Yunjun Gao, Shu Shen, Wei Zhang, Dan Luo, Lu Chen
  VLDB demo 2024 | Paper

• DESIRE: An Efficient Dynamic Cluster-based Forest Indexing for Similarity Search in Multi-Metric Spaces
  Yifan Zhu, Lu Chen, Yunjun Gao, Baihua Zheng, Pengfei Wang
  VLDB 2022 | Paper

• Question Calibration and Multi-Hop Modeling for Temporal Question Answering
  Chao Xue, Di Liang, Pengfei Wang, Jing Zhang
  AAAI 2024 | Paper