Research Homepage

Tianyu Fan

Ph.D. Student in Computer Science, The University of Hong Kong

I work on LLMs, autonomous agents, and retrieval-augmented generation, with a current focus on practical systems that make advanced reasoning more accessible and efficient.

Affiliation
Department of Computer Science, HKU
Email
tianyufan0504 AT gmail.com
Advisors
Prof. Chao Huang and Prof. Benjamin C.M. Kao

About

I am currently a first-year Ph.D. student at the Department of Computer Science in The University of Hong Kong, supervised by Prof. Chao Huang and Prof. Benjamin C.M. Kao. My research focuses on LLMs, agents and RAG.

Education

2020 - 2024

Zhejiang University

B.Eng. in Automation

Advisor: Prof. Wei Jiang

Open-Source Projects

Auto-Deep-Research logo

Auto-Deep-Research

An open-source and cost-efficient alternative to OpenAI's Deep Research, based on our AutoAgent framework. It ranks first among open-source methods and delivers performance comparable to OpenAI's Deep Research.

GitHub stars GitHub forks GitHub stars GitHub forks
AI-Trader logo

AI-Trader

A benchmark for autonomous agents in real-time financial markets, accompanying the AI-Trader paper.

GitHub stars GitHub forks

ClawWork

OpenClaw as your AI coworker for collaborative research and agentic workflows.

GitHub stars GitHub forks

Publications

PDF icon pdf

DeepInnovator: Triggering the Innovative Capabilities of LLMs

Tianyu Fan, Fengji Zhang, Yuxiang Zheng, Bei Chen, Xinyao Niu, Chengen Huang, Junyang Lin, Chao Huang

ArXiv: 2602.18920

PDF icon pdf

AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets

Tianyu Fan, Yuhao Yang, Yangqin Jiang, Yifei Zhang, Yuxuan Chen, Chao Huang

ArXiv: 2512.10971 GitHub stars

PDF icon pdf

Understanding DeepResearch Via Reports

Tianyu Fan, Xinyao Niu, Yuxiang Zheng, Fengji Zhang, Chengen Huang, Bei Chen, Junyang Lin, Chao Huang

ArXiv: 2510.07861

PDF icon pdf

AutoAgent: Fully-Automated & Zero-Code LLM Agent Framework

Jiabin Tang, Tianyu Fan, Chao Huang

ArXiv: 2502.05957 GitHub stars

PDF icon pdf

MiniRAG: Towards Extremely Simple Retrieval-Augmented Generation

Tianyu Fan, Jingyuan Wang, Xubin Ren, Chao Huang

ArXiv: 2501.06713 GitHub stars

PDF icon pdf

Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks

Tianyu Fan, Lirong Wu, Yufei Huang, Haitao Lin, Cheng Tan, Zhangyang Gao, Stan Z. Li

ICLR 2024

PDF icon pdf

Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns

Yifei Sun, Qi Zhu, Yang Yang, Chunping Wang, Tianyu Fan, Jiajun Zhu, Lei Chen

AAAI 2024

PDF icon pdf

Extracting Low-/High-Frequency Knowledge from Graph Neural Networks and Injecting it into MLPs: An Effective GNN-to-MLP Distillation Framework

Lirong Wu, Haitao Lin, Yufei Huang, Tianyu Fan, Stan Z. Li

AAAI 2023 (Oral)

Experiences

Mar. 2025 - Present

Research Intern, Qwen Team, Alibaba Group

Advisor: Dr. Bei Chen

Building Qwen-DeepResearch system.

Dec. 2023 - Feb. 2024

Research Intern, MSRA, Microsoft

Mentors: Dr. Xiao Yang and Dr. Weiqing Liu

Dec. 2022 - Mar. 2023

Research Intern, AI-Net, Zhejiang University

Advisor: Prof. Yang Yang

Jun. 2022 - Nov. 2022

Research Intern, AI Lab, Westlake University

Advisor: Prof. Stan Z. Li

Honors & Awards

2024Hong Kong PhD Fellowship Scheme (HKPFS)
2024HKU Presidential PhD Scholar (HKUPS)
2022, 2023Zhejiang Provincial Government Scholarship

Service

Program Committee Member: ICML 2026; ICLR 2025, 2024; AAAI 2025; CIKM 2023

Last update: Mar. 2026.