Jiang Shutong (江姝潼)

Jiang Shutong (江姝潼)

Master Student @ Tsinghua University

About me

Jiang Shutong (江姝潼)

Hi, I’m Shutong Jiang (江姝潼), a second-year Master student at Tsinghua University (THU), supervised by Prof. Yingbo Liu in the school of Software.

I have gained extensive industry experience through algorithm internships at Microsoft (MAI), Alibaba (Qwen). Now I am interning at Hunyuan Group(Tencent) as a research intern.

My research interests focus on the field of LLM Agents, with specific interests in Agentic Systems, Long-horizon Planning, and LLM Reasoning. If you are interested in my research, please feel free to contact me.

Email: jiangst23@mails.tsinghua.edu.cn
GitHub / Google Scholar

Education

  • Tsinghua University
    • M.S. in Software Engineering, School of Software
    • Sept. 2023 - June 2026 (Expected)
    • Supervised by Prof. Yingbo Liu. My research interests are in the field of LLM Agents and RAG.
  • Beijing University of Posts and Telecommunications (BUPT)
    • B.E. in Network Engineering, School of Computer Science
    • Sept. 2019 - June 2023
    • Ranked 1st in major, recommended for admission to Tsinghua University

Publications

  • DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints Shutong Jiang, et al.
    arXiv preprint, 2026. [Link]

  • Qwen-3 Technical Report An Yang, Anfeng Li, …, Shutong Jiang, …, et al.
    arXiv preprint, 2025. [Link]

  • Qwen3-VL Technical Report Shuai Bai, Yuxuan Cai, …, Shutong Jiang, …, et al.
    arXiv preprint, 2025. [Link]

Experience

Alibaba Tongyi Lab

Duties: Algorithm Intern (Agent Group)

  • MCP Integration & Paradigm Optimization: Designed a “Planning-Action-Reflection” framework for Qwen3 Agents, enhancing model reasoning and task decomposition.
  • Qwen-VL Agent System: Constructed a three-stage data pipeline for multimodal tool-calling, introducing “Zoom-in & Search” patterns for complex visual reasoning.
  • Agent Pre-training: Developed a large-scale data generation pipeline for tool-use, producing over 2.38M high-quality trajectories (9.6B tokens) to internalize agentic capabilities.

01.AI (Lingyi Wanwu)

Duties: Algorithm Intern (Alignment & RL Group)

  • Novel Writing Agent: Built a Multi-Agent framework utilizing Role-Playing paradigms to automate long-form fiction creation.
  • Dynamic Memory Mechanism: Implemented an LLM-driven memory system with sliding window updates to ensure character and plot consistency in large-scale narratives.

Microsoft

Duties: Algorithm Intern (Edge Machine Learning Group)

  • Edge Copilot Optimization: Fine-tuned 8B-scale open-source models for automatic browser tab grouping, achieving a 78% user click-acceptance rate.
  • Fine-grained Alignment: Utilized DPO and divide-and-conquer strategies to align model outputs with user preferences for balanced grouping granularity.

Honors & Awards

  • Tsinghua-Friend Ningde Apprentice Scholarship, 2024
  • Excellent Student Leader, Tsinghua University, 2023
  • National Scholarship, 2021
  • Outstanding Graduate of Beijing, 2023
  • Huawei Scholarship (School-Enterprise Cooperation), 2020

Skills

  • Programming: Proficient in Python; experienced with PyTorch and data science libraries (Numpy, Pandas, Matplotlib).
  • Professional: Deep understanding of LLM Agents, RAG, and fine-tuning techniques; skilled in Llama-Factory and Megatron frameworks.
  • Language: Excellent English proficiency (CET-6: 586, TOEFL: 97), capable of writing professional technical documentation.