Mian Zhang

Hi, I'm a CS PhD in UTD, advised by Zhiyu Zoey Chen. I was a research intern at Zoom Gen AI, Tencent AI Lab and a member of the NLP group at Soochow University.

I am seeking a Research Internship related to LLMs next summer. Please reach out if you have any opportunities!

Research

Recently, I'm mainly working on post-training and synthetic data generation to make LLMs more controllable. Research topics includes complex instruction following (LogicIF), smart agentic search (Search Wisely), and instruction hierarchy enforcing (TBD).

SELECTED PUBLICATIONS

* equal contribution

Complex Logical Instruction Generation

Mian Zhang, Shujian Liu, Sixun Dong, Ming Yin, Yebowen Hu, Xun Wang, Steven Ma, Song Wang, Sathish Reddy Indurthi, Haoyun Deng, Zhiyu Zoey Chen, Kaiqiang Song

Preprint

code and benchmark

Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty

Peilin Wu*, Mian Zhang*, Xinlu Zhang, Xinya Du, Zhiyu Zoey Chen

EMNLP 2025

code

LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

Ming Yin, Dinghan Shen, Silei Xu, Jianbing Han, Sixun Dong, Mian Zhang, Yebowen Hu, Shujian Liu, Simin Ma, Song Wang, Sathish Reddy Indurthi, Xun Wang, Yiran Chen, Kaiqiang Song

Preprint

code and benchmark (coming soon)

MMTok: Multimodal Coverage Maximization for Efficient Inference of VLMs

Sixun Dong, Juhua Hu, Mian Zhang, Ming Yin, Yanjie Fu, Qi Qian

Preprint

Project Page

IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction

Kaiyu He, Mian Zhang, Shuo Yan, Peilin Wu, Zhiyu Zoey Chen

ACL 2025

code and data

LMR-Bench: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research

Shuo Yan, Ziming Luo, Zimu Wang, Ruochen Li, Daoyang Li, Liqiang Jing, Kaiyu He, Peilin Wu, Juntong Ni, George Michalopoulos, Yue Zhang, Ziyang Zhang, Mian Zhang, Zhiyu Chen, Xinya Du

EMNLP 2025

dataset and code

SafeConv: Explaining and Correcting Conversational Unsafe Bahavior

Mian Zhang, Lifeng Jin, Linfeng Song, Haitao Mi, Wenliang Chen, Dong Yu

ACL 2023 (Oral Presentation)

dataset