About Me
I am a master's student in Artificial Intelligence at Zhejiang University, expected to graduate in June 2027. I am a member of the Interactive Data Group (IDG) at the State Key Laboratory of CAD&CG, where I am jointly advised by Prof. Yingcai Wu and Prof. Di Weng.
I study long-horizon language agents and recursive self-improvement (RSI), with a focus on AI Business Operations. Drawing on natural language processing, human-computer interaction, and agentic reinforcement learning, I explore how agents learn from feedback to improve their decisions, skills, and tools for autonomous retail operations.
News
SPADER was featured by ✦ 机器之心 (Synced).
Joined StepFun to work on AI Business.
Three papers: SPADER, BIRD-History, and Modality Fault Lines were accepted to EMNLP 2026.
One of our pull requests was merged into Hermes.
MerchantBench ranked 🏆 #1 Paper of the Day on Hugging Face Daily Papers.
Joined Alibaba's 1688 team to work on Self-Evolving agents and long-horizon RL.
Cerebra appeared at CHI 2026 in Barcelona.
Completed a research internship at Microsoft on the Wide Search Agent.
Selected Publications
* Equal contribution; † Corresponding author