Renze Lou

Renze Lou

楼仁泽

AI Researcher

Education

Academic

Ph.D. in Computer Science

2022 - Present

Penn State Univ.

M.S. in Computer Science

2022 - 2025

Penn State Univ.

B.Eng. in Computer Science

2018 - 2022

ZUCC

About

Hi, I am Renze (Reza) Lou 👋, a 4th-year PhD student at Penn State University.

I am broadly interested in frontier topics in AI and large language models. My current research covers LLM post-training, instruction tuning, and agentic systems, etc.

Outside research, I enjoy road trips, exploring new restaurants (especially Chinese food), and enjoying creative AI-generated videos such as those made with Sora (e.g., 🐱, 🏀, and 🐎).

Selected Publications

The Tool Illusion: Rethinking Tool Use in Web Agents

Renze Lou, Baolin Peng, Wenlin Yao, Qianhui Wu, Hao Cheng, et al.

Preprint 2026

AAAR-1.0: Assessing AI's Potential to Assist Research

Renze Lou, Hanzi Xu, Sijia Wang, Jiangshu Du, Ryo Kamoi, et al.

ICML 2025|Also Best Paper Award @ AI4Research workshop, AAAI 2025

TravelPlanner: A Benchmark for Real-World Planning with Language Agents

Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, et al.

ICML 2024|Spotlight (3.5%)

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction-Following

Renze Lou, Kai Zhang, Jian Xie, Yuxuan Sun, Janice Ahn, et al.

Adaptive Chameleon or Stubborn Sloth: Unraveling the Behavior of Large Language Models in Knowledge Conflicts

Jian Xie, Kai Zhang, Jiangjie Chen, Renze Lou, Yu Su

ICLR 2024|Spotlight (5%)

Is Prompt All You Need? No. A Comprehensive and Broader View of Instruction Learning

Renze Lou, Kai Zhang, Wenpeng Yin

Computational Linguistics 2024

Work Experience

Microsoft Research

· Redmond, WA

Jun 2025 - Feb 2026

Research Scientist Intern

GUI Web AgentTool-use AgentMCP & Skill

Salesforce AI Research

· Palo Alto, CA

May 2024 - Aug 2024

Research Scientist Intern

Multi-AgentCoding Agent

News

2026-01

Pass M.S. defense (Master-Along-the-Way for PhD program).

2025-05

Awarded PSU CSE Best Research Assistant 2025!

2025-05

One paper accepted by ICML 2025.

2025-03

AAAR-1.0 wins Best Paper Award at the 2nd AI4Research workshop @ AAAI 2025!

2024-01

Two papers ('MUFFIN' and 'Knowledge Conflict') accepted by ICLR 2024.