Xiaozhe Li (李潇哲)

Lxxzzz@tongji.edu.cn

👋 I am a Ph.D. student at Tongji University, advised by Qingwen Liu. I am fortunate to work with Haodong Duan and Qipeng Guo. I am also a core contributor to VLMEvalKit, a toolkit for evaluating vision-language models, and the InternBootCamp Series, which focuses on synthesizing environments for LLM reasoning and agentic systems. My current research interests center on developing real-world autonomous agents and self-evolving agentic systems.

Feel free to reach out — let's explore what we can create together!

🌟 Recent Highlights

[May 2026] Our paper DMPO has been accepted @ ICML 2026.
[May 2026] Our paper TimelyMachine has been accepted as an ACL 2026 Oral presentation!
[Apr 2026] Three papers OPT-BENCH, NP-Engine and TimelyMachine have been accepted @ ACL 2026.
[Jul 2025] Our paper Information Density Principle for MLLM Benchmarks has been accepted @ ICCV 2025.

📑Selected Research Projects

A full list of publications is here. (* indicates equal contribution.)

What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents

Xiaozhe Li*, Tianyi Lyu*, Yang Li, Yichuan Ma, Peiji Li, Linyang Li, Qipeng Guo, Dahua Lin, Kai Chen

Arxiv 2026 May

Paper Github

Beyond Mode Collapse: Distribution Matching for Diverse Reasoning

Xiaozhe Li, Yang Li, Xinyu Fang, Shengyuan Ding, Peiji Li, Yongkang Chen, Yichuan Ma, Tianyi Lyu, Linyang Li, Dahua Lin, Qipeng Guo, Qingwen Liu, Kai Chen

ICML 2026

Paper Github

OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces

Xiaozhe Li, Jixuan Chen, Xinyu Fang, Shengyuan Ding, Haodong Duan, Qingwen Liu, Kai Chen

ACL 2026

Paper Github

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs

Xiaozhe Li, Xinyu Fang, Shengyuan Ding, Yang Li, Linyang Li, Haodong Duan, Qingwen Liu, Kai Chen

ACL 2026

Paper Github

Information density principle for MLLM benchmarks

Chunyi Li*, Xiaozhe Li*, Zicheng Zhang, Yuan Tian, Ziheng Jia, Xiaohong Liu, Xiongkuo Min, Jia Wang, Haodong Duan, Kai Chen, Guangtao Zhai

ICCV 2025

Paper Github

Xiaozhe Li (李潇哲)

🌟 Recent Highlights

📑Selected Research Projects

What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents

Beyond Mode Collapse: Distribution Matching for Diverse Reasoning

OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces

Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs

Information density principle for MLLM benchmarks

🎤 Invited Talks

💼 Work Experience