Home

Wentao Zhang’s personal homepage. Research Associate at NTU working on LLM Agents and Financial AI.

Wentao Zhang

Research Associate  ·  Nanyang Technological University

Hi! I am Wentao Zhang, currently a Research Associate at Nanyang Technological University, advised by Prof. Bo An. Prior to this, I worked as a Research Engineer at Skywork AI 2050 Research (Nov 2024 – Feb 2026), where I built LLM-powered multi-agent systems. I received my M.S. in Computer Science from Nanjing University and my B.S. from Tianjin University of Finance and Economics.

My research focuses on LLM-powered autonomous agents and Financial AI (AI4Finance) — with a central theme of agent self-evolution: building systems that continuously improve themselves through closed-loop experience and protocol-level self-modification.

📧 zhangwent963@gmail.com  |  💻 GitHub  |  🎓 Google Scholar

708 Citations
8 h-index
15 Papers
5+ Top Venues

News

Feb 21, 2026
STORM accepted at WSDM 2026
Spatio-temporal factor model for financial trading.
Feb 10, 2026
AlphaForgeBench accepted at KDD 2026
Benchmarking end-to-end trading strategy design with LLMs.
Aug 4, 2025
FinWorld accepted at KDD 2026
An all-in-one platform for end-to-end financial AI research.
Jun 14, 2025
AgentOrchestra released
Hierarchical multi-agent orchestration with the TEA protocol.
May 1, 2025
Cradle accepted at ICML 2025
Empowering foundation agents towards general computer control.
Feb 28, 2024
FinAgent accepted at KDD 2024
Multimodal foundation agent for financial trading.
Jan 25, 2024
TWOSOME accepted at ICLR 2024
Aligning LLMs with embodied environments via reinforcement learning.
Nov 17, 2023
EarnMore accepted at WWW 2024
Portfolio management with maskable stock representation via RL.
Sep 26, 2023
TradeMaster accepted at NeurIPS 2023
A holistic quantitative trading platform empowered by reinforcement learning.
Sep 22, 2023
EarnHFT accepted at AAAI 2024
Efficient hierarchical reinforcement learning for high-frequency trading.

Selected Publications

AgentOrchestra: Orchestrating Hierarchical Multi-Agent Intelligence with the TEA Protocol
Wentao Zhang, Liang Zeng, Yuzhen Xiao, Yongcong Li, Ce Cui, Yilei Zhao, Rui Hu, Yang Liu, Yahui Zhou, Bo An
arXiv 2025
Paper
Autogenesis: A Self-Evolving Agent Protocol
Wentao Zhang, Zhe Zhao, Haibin Wen, Yingcheng Wu, Cankun Guo, Ming Yin, Bo An, Mengdi Wang
arXiv 2026
Paper GitHub
FinAgent: A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist
Wentao Zhang, Lingxuan Zhao, Haochong Xia, Shuo Sun, Jiaze Sun, Molei Qin, Xinyi Li, Yuqing Zhao, Yilei Zhao, Xinyu Cai, Longtao Zheng, Xinrun Wang, Bo An
KDD 2024
Paper GitHub
Cradle: Empowering Foundation Agents towards General Computer Control
Weihao Tan, Wentao Zhang, Xinrun Xu, Haochong Xia, Ziluo Ding, et al.
ICML 2025
Paper GitHub Project Page
TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning
Shuo Sun, Molei Qin, Wentao Zhang, Haochong Xia, Chuqiao Zong, et al.
NeurIPS 2023
Paper GitHub

→ See all publications

© 2026. Wentao Zhang. All rights reserved.

Powered by Hydejack v9.2.1