Mingchen Li
Portrait of Mingchen Li

Mingchen Li

Ph.D. Student

Computer Science, University of Massachusetts Amherst, U.S.

mingchenli@umass.edu

CV

I am a Ph.D. student in Computer Science at the University of Massachusetts Amherst. My research focuses on large language models, agentic retrieval, deep research, reasoning, and AI for biomedicine.

My work spans two closely connected directions:

General AI: Agents, Retrieval, and Reasoning

I study how large language models can search, retrieve evidence, reason over long horizons, and use external tools to solve complex tasks. My research includes agentic retrieval, deep research systems, reinforcement learning for LLM agents, retrieval-augmented generation, and graph-based retrieval. A central goal of this work is to build agentic AI systems that are more efficient, reliable, and adaptive in open-ended environments. I am particularly interested in improving when agents retrieve, what they retrieve, how they use retrieved evidence, and how they decide when to continue, reroute, or stop.

AI for Biomedicine and Healthcare

I also develop large language models and retrieval-based systems for biomedical and clinical applications, including cancer, opioid overdose risk prediction, diagnosis prediction, biomedical information extraction, and medical question answering. In these high-stakes settings, my research focuses on improving the reliability of evidence retrieval, clinical reasoning, prediction, and domain adaptation. My broader goal is to develop AI systems that can support biomedical research and healthcare decision-making with greater accuracy, robustness, and interpretability.

Publications

Complete list: Google Scholar profile.

General AI

  1. RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents

    Mingchen Li, Hansi Zeng, Zhuo Qian, Jiatan Huang, Sunjae Kwon, Hamed Zamani, Hong Yu

    NeurIPS 2026Paper onlineGitHub Repository

  2. In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective

    Mingchen Li, Jiatan Huang, Chuxu Zhang, Liang Zhao, Hong Yu

    NeurIPS 2026Paper onlineGitHub Repository

  3. A condensed transition graph framework for zero-shot link prediction with large language models

    Mingchen Li, Chen Ling, Rui Zhang, Liang Zhao

    ICDM 2024Paper onlineGitHub Repository

  4. Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State Tracking

    Mingchen Li, Lifu Huang

    SIGIR 2023Paper onlineGitHub Repository

  5. Semantic Structure based Query Graph Prediction for Question Answering over Knowledge Graph

    Mingchen Li, Shihao Ji

    COLING 2022Paper onlineGitHub Repository

  6. A Hierarchical N-Gram Framework for Zero-Shot Link Prediction

    Mingchen Li, Junfan Chen, Samuel Mensah, Nikolaos Aletras, Xiulong Yang, Yang Ye

    EMNLP 2022 (Finding track)Paper onlineGitHub Repository

  7. Counterfactual Graph for Multi-Agent LLM Calibration

    Jiatan Huang, Mingchen Li, Ziming Li, Sunjae Kwon, Hong Yu, Chuxu Zhang

    arXiv preprint 2026Paper onlineGitHub Repository

Biomedicine & Healthcare

  1. Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction.

    Mingchen Li, Jiatan Huang, Hong Yu

    ACL 2026 FindingPaper onlineGitHub Repository

  2. CancerLLM: a large language model in cancer domain

    Mingchen Li, Zaifu Zhan, Jiatan Huang, Jeremy Yeung, Kai Ding, Anne Blaes, Steven Johnson, Hongfang Liu, Hua Xu , Rui Zhang

    NPJ Digital Medicine 2026Paper onlineGitHub Repository

  3. Benchmarking retrieval-augmented large language models in biomedical nlp: Application, robustness, and self-awareness

    Mingchen Li, Zaifu Zhan, Han Yang, Yongkang Xiao, Jiatan Huang, Rui Zhang

    Science Advance 2026Paper onlineGitHub Repository

  4. BiomedRAG: A retrieval augmented large language model for biomedicine

    Mingchen Li, Halil Kilicoglu, Hua Xu, Rui Zhang

    Journal of Biomedical Informatics (JBI) 162, 104769 2025Paper onlineGitHub Repository

  5. RT: a Retrieving and Chain-of-Thought framework for few-shot medical named entity recognition

    Mingchen Li, Huixue Zhou, Han Yang, Rui Zhang

    Journal of the American Medical Informatics Association (JAMIA) 31 (9), 1929 ... 2024Paper onlineGitHub Repository

  6. RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine

    Jiatan Huang, Mingchen Li, Dawei Li, Yuxin Zhang, Zhichao Yang, Yongkang Xiao, Feiyun Ouyang, Xiaohan Li, Shuo Han, Hong Yu

    ACL 2026 FindingsPaper onlineHugging Face datasetGitHub Repository

  7. RAMIE: retrieval-augmented multi-task information extraction with large language models on dietary supplements

    Zaifu Zhan, Shuang Zhou, Mingchen Li, Rui Zhang

    Journal of the American Medical Informatics Association (JAMIA) 32 (3), 545-554 2025Paper onlineGitHub Repository

  8. Large language model synergy for ensemble learning in medical question answering: design and evaluation study

    Han Yang, Mingchen Li, Huixue Zhou, Yongkang Xiao, Qian Fang, Shuang Zhou, Rui Zhang

    Journal of Medical Internet Research 27, e70080 2025Paper onlineGitHub Repository

  9. LEAP: LLM instruction-example adaptive prompting framework for biomedical relation extraction

    Huixue Zhou, Mingchen Li, Yongkang Xiao, Han Yang, Rui Zhang

    Journal of the American Medical Informatics Association (JAMIA) 31 (9), 2010 ... 2024Paper onlineGitHub Repository

  10. Fuselinker: Leveraging Llm's Pre-Trained Text Embeddings and Domain Knowledge to Enhance Gnn-Based Link Prediction on Biomedical Knowledge Graphs

    Yongkang Xiao, Shuang Zhang, Huixue Zhou, Mingchen Li, Han Yang, Rui Zhang

    Journal of Biomedical Informatics (JBI) 2024Paper onlineGitHub Repository

  11. A Review of Reinforcement Learning for Natural Language Processing, and Applications in Healthcare

    Ying Liu, Haozhu Wang, Huixue Zhou, Mingchen Li, Yu Hou, Shuang Zhou, Fang Wang, Rama Hoetzlein, Rui Zhang

    Journal of the American Medical Informatics Association (JAMIA) 2023Paper onlineGitHub Repository

Experience

  • PhD Student, Computer Science, UMass Amherst. 09.2024 - Present
  • Researcher, University of Minnesota Twin Cities. 01.2023 - 08.2024
  • Teaching Assistant, Georgia State University, Deep Learning (CSC 8850). 09.2021 - 12.2021
  • Research Assistant, Georgia State University. 01.2021 - 05.2021

Service

  • Reviewer — Journals: Artificial Intelligence in Medicine, Engineering Applications of Artificial Intelligence, Expert Systems with Applications, Information Processing & Management, International Journal of Medical Informatics, Journal of Artificial Intelligence Research, Knowledge-Based Systems, Npj Health Systems
  • Reviewer — Conferences: EMNLP 2022, ACL 2023, EMNLP 2023, EMNLP Industry Track 2023, IEEE ICHI 2023, NAACL 2024, EMNLP 2026, NIPS 2026, AAAI 2027

Contact

Google Scholar: scholar profile

GitHub: ToneLi

Email: mingchenli@umass.edu