Yingjin JIANG（江英进）
MPhil Student at HKUST(GZ) · LLM Agents · Reinforcement Learning
I am a first-year MPhil student at The Hong Kong University of Science and Technology (Guangzhou), with a dedicated research focus on Large Language Model (LLM) Agents. My work centers on enhancing the complex reasoning and decision-making capabilities of agents, primarily through developing sophisticated reinforcement learning strategies. I have previously led research that improved LLM mathematical reasoning by designing multi-dimensional reward functions. I am actively seeking a research internship at a top-tier lab to contribute to challenging projects in agentic AI.
Research Interests
- Large Language Model (LLM) Agents
- Reinforcement Learning
Education & Background
Hong Kong University of Science and Technology (Guangzhou)
Red Bird MPhil in Artificial Intelligence (2025-2027)
University of Macau
Exchange Program in Computer Science (2023)
- GPA: 3.85/4.0
Awards & Honors
- National Scholarship (2023)
- Tencent Scholarship (Grand Prize) (2023)
- HUAWEI Scholarship (2022)
- Outstanding Thesis Award (2025/06)
- Challenge Cup National 2nd Prize (2024/11)
- APMCM International 2nd Prize (2023/02)
- MCM Honorable Mention (2023/05)
Collaboration Focus
- Solve challenging problems at the intersection of AI research and systems engineering
- Work with world-class mentors who push the boundaries of what's possible
- Make real impact by developing technologies that benefit society
- Collaborate with brilliant minds in a fast-paced, innovative environment