About
My name is Yiyang (Ian) Li, a second-year Ph.D. student in the Department of Computer Science and Engineering at the University of Notre Dame. My advisor is Prof. Yanfang (Fanny) Ye. Before joining Notre Dame, I received my B.E. degree in Artificial Intelligence from Northeastern University (China) in 2024.
My research focuses on agentic AI systems and large foundation models, with the goal of enabling models to reason, act, and collaborate effectively in complex, real-world environments. I am particularly interested in self-evolving agents, agent system optimization, as well as retrieval-augmented generation and knowledge-guided reasoning. For more details, please check my CV here.
News
One paper is accepted to EACL 2026 Findings.
We have released LLMs4ALL, an extensive survey on LLMs for research and applications in academic disciplines.
NGQA is accepted to ACL 2025 main conference.
Selected Publications
EvoTaxo: Building and Evolving Taxonomy from Social Media Streams
Yiyang Li, Tianyi Ma, Yanfang Ye
Preprint 2026
EvoTaxo is a novel framework for constructing and evolving taxonomies from social media data, enabling dynamic organization and retrieval of information in rapidly changing domains.
LongDA: Benchmarking LLM Agents for Long-Document Data Analysis
Yiyang Li, Zheyuan Zhang, Tianyi Ma, Zehong Wang, Keerthiram Murugesan, Chuxu Zhang, Yanfang Ye
Preprint 2026
This paper introduces LongDA, a benchmark and agent framework for evaluating data analysis agents using complex, real-world datasets and documentation.
Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use
Yiyang Li†, Zehong Wang†, Zhengqing Yuan, Zheyuan Zhang, Keerthiram Murugesan, Chuxu Zhang, Yanfang Ye
EACL Findings 2026
This paper introduces LAMI, an interpretable graph-language model designed to detect illicit drug use among youth by modeling survey text to structured representations.
NGQA: a nutritional graph question answering benchmark for personalized health-aware nutritional reasoning
Zheyuan Zhang†, Yiyang Li†, Nhi Ha Lan Le†, Zehong Wang, Tianyi Ma, Vincent Galassi, Keerthiram Murugesan, Nuno Moniz, Werner Geyer, Nitesh V Chawla, Chuxu Zhang, Yanfang Ye
ACL 2025
NGQA is a novel question answering benchmark designed to evaluate models' capabilities in personalized health-aware nutritional reasoning using knowledge graphs.
Teaching
Courses I have taught or assisted with.
Computer Security
2026 SpringTeaching Assistant
Introduction to Artificial Intelligence
2024 FallTeaching Assistant