About
Hello there! I’m Kehang.
I’m a final year Ph.D. candidate at Harvard University. I’ve been jointly advised by Prof. John Horton from MIT Sloan’s IT group and Prof. David Parkes from Harvard’s EconCS group. I had the pleasure to intern in Google DeepMind and worked with Crystal Qian, Nithum Thain and James Wexler.
I study AI agents as proxies for human decision-making and how individuals collaborate with these agents in economic environments.
My research has two primary strands.
First, I examine the capabilities, benefits, and trade-offs of deploying large language models (LLMs) as autonomous agents. I develop novel AI tools and run large-scale economic experiments to understand when and how LLM agents replicate, augment, or diverge from human behavior.
Second, I use LLM-based simulations to uncover new patterns in human decision-making and to design more effective interventions, market mechanisms, and organizational policies. By combining computational modeling with experimental economics, my work aims to inform the responsible deployment of AI in markets and institutions.
My Research
Automated Social Science: Language Models as Scientist and Subjects
With Benjamin Manning* and John Horton .
Reject and Resubmit at the Quarterly Journal of Economics.
Selected Media: Marginal revolution, The Future of Being Human, One Useful Thing,
Strategic Tradeoffs Between Human and AI Agents in Bargaining Games
With Google DeepMind Team: Crystal Qian*, Vivian Tsai, James Wexler, Nithum Thain and John Horton, Benjamin Manning
Accepted in IUI 2026
Intern work in Google DeepMind, with Nithum Thain, Vivian Tsai, James Wexler, Crystal Qian
Learning from Synthetic Laboratory: Language Models as Auction Participants
With Anand Shah*, Jeffery Wang, Arif K. Dayi, Yanchen Jiang, John Horton and David Parkes
NeurIPS 2024 (Workshop), EC 2024 (Poster)
My Journey So Far
Before joining Harvard, I was very lucky, undeservedly so, to be host by Nobel Laureate in Physics Prof. Frank Wilczek in MIT. I was working on using Quantum field theory to model correlated dynamics inside a class of material (quantum spin ice) News.
My research interests turned to human and society after an enriching collaboration with Prof. Hanspeter Pfister from Harvard Viusal Computing Group. I ran large-scale human-subject studies to investigate the mental models of people making sense of visualizations CHI 24’. Reading Between the Pixels: Investigating the Barriers to Visualization Literacy
Recently, I was selected as the Introduction to Technical AI Safety Fellow with the AI Safety Student Team
A Pinch of Extra
When I’m not geeking out over research, you can find me capturing the world through my camera lens 📸, embracing the beauty of nature 🌲, hitting the ski slopes 🎿, or trekking through scenic trails 🥾.
Selected Honors
- Google DeepMind Seed Fund, 2024
- Introduction to Technical AI Safety Fellowship, 2023
- Purcell Fellowship (Harvard), 2021
- Guo Moruo Scholarship (Highest honor for USTC undergrad students), 2020
- Yan Jici Scholarship (Highest honor for Physics department undergrad students), 2020