Bio

I am currently a M.S. student at the University of Washington. At UW, I am fortunate to work with Ph.D. Student Rulin Shao, Prof. Pang Wei Koh, and Prof. Akari Asai. I used to intern at ByteDance Seed and Shanghai AI Laboratory. I obtained my B.S. in Computer Science from Jilin University.

Research Interests

  • Deep Research Agents
  • Test time scaling
  • Human LLM collaboration

News

  • Feb. 2026
    Our DR Tulu demo is released, please check it out!
  • Nov. 2025
    Our DR Tulu paper is released on arXiv, this is the first fully open source deep research agent!
  • Sep. 2025
    Started my M.S. journey at UW!

Publications

DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Rulin Shao*, Akari Asai*, Shannon Zejiang Shen*, Hamish Ivison*, Varsha Kishore†, Jingming Zhuo† (core contributor), Xinran Zhao, Molly Park, Samuel G. Finlayson, David Sontag, Tyler Murray, Sewon Min, Pradeep Dasigi, Luca Soldaini, Faeze Brahman, Wen-tau Yih, Tongshuang Wu, Luke Zettlemoyer, Yoon Kim, Hannaneh Hajishirzi, Pang Wei Koh

Preprint 2025

Paper Code Demo

ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs

Jingming Zhuo*, Songyang Zhang*, Xinyu Fang, Haodong Duan, Dahua Lin, Kai Chen

EMNLP Findings 2024

Paper Code

InternLM2 Technical Report

Zheng Cai, ..., Jingming Zhuo, ... (alphabetical order by last name)

Technical Report 2024

Paper GitHub

T-eval: Evaluating the Tool Utilization Capability Step by Step

Zehui Chen*, Weihua Du*, Wenwei Zhang*, Kuikun Liu, Jiangning Liu, Miao Zheng, Jingming Zhuo, Songyang Zhang, Dahua Lin, Kai Chen, Feng Zhao

ACL 2024

Paper GitHub

Projects

DR Tulu

A reinforcement learning framework for deep research that uses evolving rubrics to improve planning, evidence grounding, and long-form report quality.

GitHub stars for rlresearch/dr-tulu

Seed1.5-Embedding

A strong embedding model focused on retrieval and reasoning quality, designed for robust performance on benchmarks such as MTEB and BRIGHT.

InternLM

An open large language model family with training, alignment, and evaluation components for general-purpose NLP and agent-style use cases.

GitHub stars for InternLM/InternLM

OpenCompass

An extensible LLM evaluation platform that supports diverse benchmarks across code, agents, long context, math, and instruction following.

GitHub stars for open-compass/opencompass

Education

  • M.S. in ECE

    University of Washington University of Washington logo

    Sep. 2025 - Present

  • B.S. in CS

    Jilin University Jilin University logo

    Sep. 2020 - Jun. 2024

Experience

  • Research Assistant

    UW NLP

    Working on deep research agents.

    Sep. 2025 - Present

  • Research Intern

    ByteDance Seed

    Worked on reasoning-intensive retrieval.

    Mar. 2025 - Sep. 2025

  • Research Intern

    Shanghai AI Laboratory

    Worked on LLM post-training and evaluation.

    Sep. 2023 - May. 2024

Service

  • Reviewer

    ICLR, ICML, ACL, EMNLP, NAACL, COLING

Misc

  • Piano
  • Music
  • Travel
  • Snowboard