• [2025/7] We are organizing a Workshop on Information Economics x LLMs at EC'25 at Stanford!
• [2025/4] I will attend ICLR'25 in Singapore to present our spotlight paper “Generalized Principal-Agent Problem with a Learning Agent”!
• [2025/1] I will attend ITCS'25 in New York to present our work “Information Design with Unknown Prior”; see video.
• ….

My research direction is learning-based incentive design, an interdiscplinary topic in economics, machine learning, and theoretical computer science. I study mechanism design and information design problems with learning-based decision-makers. Example directions include:

• Learning agents: I investigate how the learning behavior of boundedly rational agents (modeled by, e.g., reinforcement learning) affects the outcome of games, compared to the outcome predicted by the traditional rational-agent-based economic theory.
• Learning principals: I also study how the principals (designers of mechanisms and information structures) can achieve the optimal design goals by learning unknown parameters about the agents and the environments from repeated interactions. Involving dynamic and strategic data sources, this learning problem departs from the canonical machine learning paradigm that assumes stationary and exogenous data distributions, requiring new methodologies that I aim to develop.

My research is often motivated by the interplay between economic incentives and machine learning algorithms in real-world AI systems, such as advertising auctions and recommender systems.