Tsinghua University · Electronic Engineering

Jinghua Piao 朴景华

Postdoctoral Researcher · Future Intelligence Lab

Understanding human–AI systems. Building artificial societies.

Jinghua Piao
Beijing, China

I am a postdoctoral researcher in the Department of Electronic Engineering at Tsinghua University, working with Prof. Yong Li at the Future Intelligence Lab. I received my Ph.D. (2026) and M.Eng. (2022) from Tsinghua University, advised by Prof. Yong Li, and my B.Eng. from Tianjin University (2019).

My research lies at the intersection of artificial intelligence, complex systems, and computational social science. I study how people and intelligent algorithms shape one another, how collective behavior emerges in networks of LLM agents, and how we can build useful artificial societies for social science.

My work has appeared in Nature Machine Intelligence and Nature Communications. I lead the development of AgentSociety, an open research platform for large-scale social simulation and computational experiments.

Research interests

Human–AI Interaction

Feedback loops between people and algorithms, information cocoons, and the social impact of recommendation.

LLM Agents & Social Intelligence

Social cognition, opinion dynamics, and collective behavior in networks of intelligent agents.

Computational Social Science

Large-scale artificial societies and reproducible experiments for social and economic systems.

Research highlights

From mechanisms to artificial societies
naturemachine intelligence
Nature Machine Intelligence · 2023

Why information cocoons emerge

Revealing how the adaptive feedback between human preferences and recommendation algorithms drives the loss of information diversity.

naturecommunications
Nature Communications · 2026

When AI societies polarize

Showing how polarization emerges in networks of LLM agents, and using these systems to investigate social mechanisms and possible interventions.

naturemachine intelligence
Nature Machine Intelligence · Accepted

Why AI collectives lose diversity

Investigating persistent semantic convergence in interacting LLM systems, even when their wording varies. Joint work with Weiyi Kong, Shiyang Lai, and James Evans.

AgentSocietyLLM agents in society

Open-source research platformOpen-source code ↗

An open platform for studying human behavior and society with LLM agents—from large-scale social simulation to an integrated workflow for computational experiments.

1.0Large-scale social simulation

LLM agents interacting in realistic social environments.

2.0Executable social science

AI social scientists connecting hypotheses, simulations, and analysis.

Recent news

Publications

Google Scholar ↗

2026

2025

2024

2023

2022

2021

2019

Undated manuscripts

Education & experience

  1. Postdoctoral Researcher · Tsinghua University

    Department of Electronic Engineering · Advisor: Prof. Yong Li

  2. Ph.D. · Tsinghua University

    Information and Communication Engineering · Advisor: Prof. Yong Li

  3. M.Eng. · Tsinghua University

    Electronics and Communication Engineering · Advisor: Prof. Yong Li

  4. B.Eng. · Tianjin University

    Communication Engineering

Selected honors

  • Gold ReviewerInternational Conference on Machine Learning (ICML)
  • Outstanding Doctoral DissertationTsinghua University
  • Outstanding Doctoral GraduateTsinghua University
  • Outstanding Master's Thesis & GraduateTsinghua University
  • National Scholarship · Three consecutive yearsTianjin University

Academic service

Journal reviewer
Nature Human Behaviour
Conference reviewer
NeurIPS · ICLR · ICML · The Web Conference (WWW) · AAAI
Community
AgentSociety open-source platform, agent competitions, and interdisciplinary collaboration in computational social science.

Let’s connect.

I welcome conversations and collaborations on social intelligence, human–AI systems, and computational experiments with artificial societies.