Zhang Xuanming

About Me

Welcome to my homepage. I am a research scientist in Qwen Team, Alibaba Group. Previously, I was researcher at Stanford University, Peking University. My work explores the potential for digital life with artificial intelligence alignment and beyond, with a main focus on Social Intelligence: Cognitive Learning (Build), World Simulation (Test), and Impact Modeling (Iterate). I am also interested in AI application in world factors, represented by quantitative finance and agentic system. If you are insteresting in working with me, please feel free to contact!

700+

Citations

h-index

Recent Publications

📝 See full list in my Google Scholar page 🎉 Sep 2025: MetaMind received NeurIPS 2025 Spotlight 📍 June 2025: Invited to AI Startup School by Y Combinator

Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models

Xuanming Zhang, Yuxuan Chen, Samuel Yeh, Sharon Li

ACL 2026 under review

Paper Github

Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions

Yang Xu*, Xuanming Zhang*, Samuel Yeh, Jwala Dhamala, Ousmane Dia, Rahul Gupta, Sharon Li

ICLR 2026

Paper Github

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

Xuanming Zhang, Yuxuan Chen, Samuel Yeh, Sharon Li

NeurIPS 2025 Spotlight

Paper Github

Human Decision-making is Susceptible to AI-driven Manipulation

Sahand Sabour, June M. Liu, Chris Yao, Siyang Liu, Shiyao Cui, Xuanming Zhang, et al.

Nature under minor revision

Paper

SocialEval: Evaluating Social Intelligence of Large Language Models

Jinfeng Zhou, Yuxuan Chen, Yihan Shi, Xuanming Zhang, et al.

ACL 2025

Official

Generalization or Memorization: Evaluating Data Contamination for Large Language Models

Yihong Dong, Xue Jiang, Xuanming Zhang, Huanyu Liu, Zhi Jin, Bin Gu, Mengfei Yang, Ge Li

TSE under minor revision

Paper

Experience

Research Scientist

Qwen Team, Alibaba Group

2026 -

Developing and optimizing new generation of Qwen.

Research Scholar

Amazon AGI

2025 - 2026

Defining and tracking AI deception. Aligning and optimizing new generation of LLMs.

AI Framework Architect

ByteDance

2024 - 2025

Developing and optimizing AI frameworks for large-scale agent systems.

Research Scientist Intern

Zhipu AI

2024 - 2025

Research and development of advanced AI algorithms and deep learning models.

Chief Technology Officer

H3O

2021 - 2022

Leading technology strategy and development as CTO of a startup.

Get In Touch

About Me

Recent Publications

Cognition-of-Thought Elicits Social-Aligned Reasoning in Large Language Models

Simulating and Understanding Deceptive Behaviors in Long-Horizon Interactions

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

Human Decision-making is Susceptible to AI-driven Manipulation

SocialEval: Evaluating Social Intelligence of Large Language Models

Generalization or Memorization: Evaluating Data Contamination for Large Language Models

Experience

Research Scientist

Research Scholar

AI Framework Architect

Research Scientist Intern

Chief Technology Officer

Get In Touch

Email

Profile

Connect