Hi, I am Yifei Zhang (张逸飞), a master's student in Financial Engineering and Fintech at Nanjing University's School of Management & Engineering, advised by Prof. Honghai Yu. I hold a bachelor's degree in Computer Science and Technology from the Department of Computer Science and Technology at Nanjing University, where I specialized in Computer & Financial Engineering Experimental Class (a Top Talent Program).

Currently, I am a research intern at Microsoft Research Asia (MSRA), advised by Xiao Yang, focusing on Autonomous Agent research. Previously, I had the privilege of collaborating with Prof. Benyou Wang and Prof. Qianqian Xie on exploring Large Language Models in Finance.

I have published at top-tier conferences including NeurIPS and NAACL. Notably, one of my papers received the Best Paper Award at the ICLR 2025 Workshop on Advances in Financial AI, where I presented it as an oral presentation in Singapore. My research interests span Narrative Economics, Financial Applications of LLMs, and Multi-Agent Systems.

News

Selected Publications

* indicates equal contribution · Google Scholar · Detailed Publications

R&D-Agent: An LLM-Agent Framework Towards Autonomous Data Science
Xu Yang, Xiao Yang, Shikai Fang, Yifei Zhang, Jian Wang, et al.
Top-performing Open-source ML engineering agent on MLE-bench
arXiv preprint 2025
TL;DR: A comprehensive, decoupled framework that formalizes the machine learning engineering process into Research and Development phases and six components, achieving 35.1% any medal rate on MLE-Bench, SOTA among existing open-source ML engineering agents.
AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets
Tianyu Fan, Yuhao Yang, Yangqin Jiang, Yifei Zhang, Yuxuan Chen, Chao Huang, et al.
🚀 Fully-automated and data-uncontaminated benchmark for LLM agents in finance
arXiv preprint 2025
TL;DR: A comprehensive benchmark for evaluating autonomous trading agents in real-time financial markets across NASDAQ 100, SSE 50, and cryptocurrency markets, enabling fair comparison of AI trading strategies.
TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
Yuzhe Yang*, Yifei Zhang*, Minghao Wu*, Kaidi Zhang, Yunmiao Zhang, et al.
🏆 Best Paper Award @ ICLR 2025 Workshop on Advances in Financial AI (1/53)
NeurIPS 2025
TL;DR: A multi-agent simulation platform for financial markets that integrates behavioral economics and social network dynamics, enabling large-scale market experiments with diverse agent behaviors.
UCFE: A User-Centric Financial Expertise Benchmark for Large Language Models
Yuzhe Yang*, Yifei Zhang*, Yan Hu*, Yilin Guo, Ruoli Gan, et al.
NAACL Findings 2025
TL;DR: A comprehensive benchmark evaluating LLMs' financial expertise from a user-centric perspective, covering domain knowledge, application capabilities, and trustworthiness across 300+ real-world questions.

Projects

R&D-Agent
Automates the industrial R&D process with two key components: 'R' for proposing new ideas and 'D' for implementing them. Focuses on data-driven scenarios to streamline model and data development.
Multi-Agent AutoML Open Source
AI-Trader
An autonomous trading system where AI agents compete in NASDAQ 100, SSE 50, and cryptocurrency markets. Zero human intervention with pure algorithmic competition and strategy evolution.
FinTech Trading AI Agent

Experiences

Microsoft Research Asia (MSRA)
2025.05 – Present
Research Intern
Focusing on Autonomous Agent research | Advised by Xiao Yang
Nanjing University
2024.09 – Present
Master's Student in Financial Engineering and Fintech
School of Management & Engineering | Advised by Prof. Honghai Yu
CUHK-Shenzhen NLP Group
2024.07 – 2025.05
Research Assistant
Exploring Large Language Models in Finance | Advised by Prof. Benyou Wang
Nanjing University
2020.09 – 2024.06
Bachelor in Computer Science and Technology
Computer & Financial Engineering Experimental Class (Top Talent Program)
×

WeChat QR Code

WeChat QR Code

Scan the QR code to add me on WeChat