Yi Luo (罗懿)
I am currently a first-year Ph.D. student at the Hong Kong Institute of AI for Science and the Department of Biostatistics, College of Computing, City University of Hong Kong, advised by Prof. Jun Yan. I received a M.S. in Computer Science from the School of Informatics, Xiamen University in 2026, advised by Prof. Chen Lin, and a B.E. in Artificial Intelligence from the School of Informatics, Xiamen University in 2023.
🧐 Research Interests
Currently, my research interests are primarily focused on Large Language Models (LLMs), covering the following topics:
Research Agents: Investigating autonomous LLM-driven agents for scientific research (e.g., hypothesis generation and experimental design) and human-computer interaction, leveraging multimodal reasoning and tool-augmented architectures.
Self-Evolving Agents: Investigating LLM-based agents that autonomously improve themselves through experience — accumulating knowledge, refining strategies, and enhancing tool use over time to tackle increasingly complex tasks without human intervention.
AI Safety: Developing robust defense mechanisms for both LLMs and agents against adversarial attacks, data poisoning, jailbreaking, and agent-specific threats (e.g., tool misuse and unsafe autonomous behavior), while maintaining utility.
🤝 Looking for collaboration! If you are interested in working with me, please drop me an email.
🔥 News
2025.05: 🎉🎉 One paper (BioResearcher) is accepted by SCIENCE CHINA Information Sciences!
2025.05: 🎉🎉 One paper (DQABench & DQATestbed) is accepted by KDD 2025!
2024.03: 🎉🎉 Two papers (Guide-Align, Iter-CoT) are accepted by NAACL 2024!
📝 Publications
[SCIENCE CHINA Information Sciences] From intention to implementation: Automating biomedical research via llms, Yi Luo, Linghang Shi, Yihao Li, Aobo Zhuang, Yeyun Gong, Ling Liu, Chen Lin
[KDD 2025] Revolutionizing Database Q&A with Large Language Models: Comprehensive Benchmark and Evaluation, Yihang Zheng, Bo Li, Zhenghao Lin, Yi Luo, Xuanhe Zhou, Chen Lin, Jinsong Su, Guoliang Li, Shifu Li
[NAACL 2024] Ensuring Safe and High-Quality Outputs: A Guideline Library Approach for Language Models, Yi Luo, Zhenghao Lin, Yuhao Zhang, Jiashuo Sun, Chen Lin, Chengjin Xu, Xiangdong Su, Yelong Shen, Jian Guo, Yeyun Gong.
[NAACL 2024 Findings] Enhancing Chain-of-Thoughts Prompting with Iterative Bootstrapping in Large Language Models, Jiashuo Sun*, Yi Luo*, Yeyun Gong, Chen Lin, Yelong Shen, Jian Guo, Nan Duan.
[Under Review] Generalized Category Discovery in Event-Centric Contexts: Latent Pattern Mining with LLMs, Yi Luo*, Qiwen Wang*, Junqi Yang, Luyao Tang, Zhenghao Lin, Zhenzhe Ying, Weiqiang Wang, Chen Lin
[Under Review] HiCaM: A Hierarchical-Causal Modification Framework for Long-Form Text Modification, Yuntao Shi, Yi Luo, Yeyun Gong, Chen Lin
📖 Educations
2026.09 - Present, Ph.D. in Biostatistics, Hong Kong Institute of AI for Science & Department of Biostatistics, College of Computing, City University of Hong Kong (Advisor: Prof. Jun Yan)
2023.09 - 2026.06, M.S. in Computer Science, Xiamen University (Advisor: Prof. Chen Lin)
2019.09 - 2023.06, B.S. in Computer Science, Xiamen University
💻 Internships Experiences
2025.01 - 2025.05, Machine Intelligence Department, Ant Group, Research Intern
2023.09 - 2024.12, Microsoft Research Asia, Research Assistant