I work toward AI agents that learn from experience to solve complex, long-horizon tasks. To advance this goal, I study how to guide larger models with smaller ones (Matryoshka Pilot), train long-horizon agents through on-policy data aggregation (Agent DAgger), and develop the training infrastructure (STACX), data and environments (MLE-Dojo), and evaluation methods (DREAM) needed for sustained agent improvement.

I am a third-year Ph.D. student in Computational Science and Engineering at Georgia Tech, co-advised by Bo Dai and Chao Zhang.

Currently, I am a Student Researcher at ByteDance Seed, where I help advance the long-horizon agentic capabilities of frontier models.

Previously, I received my B.Eng. in Computer Science from Tsinghua University, where I was a member of the TSAIL group advised by Jianfei Chen and Jun Zhu.

Always happy to talk about research and new ideas. Feel free to reach me at cli911@gatech.edu.

News

  1. May 2026

    EDO is accepted by TMLR 2026.

  2. Apr 2026

    DREAM, an agentic evaluation framework for Deep Research agents, is accepted to ACL 2026 as an Oral presentation.

  3. Sep 2025

    Matryoshka Pilot and MLE-Dojo are accepted by NeurIPS 2025.

  4. Jun 2025

    TS-ZSQ is accepted by ICCV 2025.

Publications & Preprints

  1. Preprint2026

    Revisiting DAgger in the Era of LLM-Agents

    Changhao Li, Rushi Qiang, Jiawei Huang, Chenxiao Gao, Chao Zhang, Niao He, Bo Dai

    Paper

  2. TMLR 2026

    Exploration-Driven Optimization for Test-Time Large Language Model Reasoning

    Changhao Li, Yuchen Zhuang, Chenxiao Gao, Haotian Sun, Rushi Qiang, Chao Zhang, Bo Dai

    Paper

  3. ACL 2026 · Oral

    DREAM: Deep Research Evaluation with Agentic Metrics

    Elad Ben Avraham*, Changhao Li*, Ron Dorfman*, Roy Ganz, Oren Nuriel, Amir Dudai, Aviad Aberdam, Noah Flynn, Elman Mansimov, Adi Kalyanpur, Ron Litman

    Paper

  4. NeurIPS 2025

    Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs

    Changhao Li*, Yuchen Zhuang*, Rushi Qiang, Haotian Sun, Hanjun Dai, Chao Zhang, Bo Dai

    Paper Code

  5. NeurIPS 2025

    MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

    Rushi Qiang*, Yuchen Zhuang*, Yinghao Li, Dingu Sagar V K, Rongzhi Zhang, Changhao Li, Ian Shu-Hei Wong, Sherry Yang, Percy Liang, Chao Zhang, Bo Dai

    Paper Code

  6. ICCV 2025

    Task-Specific Zero-shot Quantization-Aware Training for Object Detection

    Changhao Li*, Xinrui Chen*, Ji Wang*, Kang Zhao, Jianfei Chen

    Paper Code

  7. NeurIPS 2023

    Training Transformers with 4-bit Integers

    Haocheng Xi, Changhao Li, Jianfei Chen, Jun Zhu

    Paper Code

* denotes equal contribution.

Software

Industry Experience

  1. ByteDance Seed

    Aug 2026 — Present

    Student Researcher

    San Jose, California, United States

  2. Qwen

    May 2026 — Aug 2026

    Research Intern

    Seattle, Washington, United States

  3. AWS AI Lab

    May 2025 — Aug 2025

    Applied Scientist Intern

    New York, United States

Academic Service

Awards & Honors

Education

  1. Aug 2024 — Present

    Ph.D. in Computational Science and Engineering

    Georgia Institute of Technology

  2. Sep 2020 — Jun 2024

    B.Eng. in Computer Science and Technology

    Tsinghua University