Jiatan HuangJiatan Huang
Ph.D. Student · Computer Science · University of Connecticut
Hello, I'm Jiatan Huang, a second-year Ph.D. student in Computer Science at the University of Connecticut, advised by Prof. Chuxu Zhang. Before joining UConn, I earned my Bachelor's degree in Computer Science from the University of Minnesota–Twin Cities. My research focuses on two directions.
Agentic AI
I build LLM-based agents and multi-agent systems that can reason, collaborate, and use external knowledge to solve complex tasks. I am especially interested in making these systems more reliable, efficient, and adaptive.
AI for Healthcare
I develop AI for medicine and healthcare, from large language models and benchmarks to knowledge-grounded reasoning. My goal is to build trustworthy AI that helps address real-world health challenges.
Beyond these two directions, I am broadly interested in graph neural networks and information retrieval. For more details, please see my CV.
Actively seeking a Research Scientist internship opportunity for Summer 2027.
Education
Publications
* equal contribution. Complete list on Google Scholar.
Agentic AI 4
- arXiv preprint 2026 Counterfactual Graph for Multi-Agent LLM Calibration
- arXiv preprint 2026 EvolveRouter: Co-Evolving Routing and Prompt for Multi-Agent Question Answering
- NeurIPS 2026 Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents
- NeurIPS 2026 RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agents
AI for Healthcare 6
- ACL 2026 Findings RiTeK: A Dataset for Large Language Models Complex Reasoning over Textual Knowledge Graphs in Medicine
- TMLR GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health
- KDD 2026 OPBench: A Graph Benchmark to Combat the Opioid Crisis
- ACL 2026 Findings Efficient and Effective Internal Memory Retrieval for LLM-Based Healthcare Prediction
- npj Digital Medicine CancerLLM: A Large Language Model in Cancer Domain
- Science Advances Benchmarking Retrieval-Augmented Large Language Models in Biomedical NLP: Application, Robustness, and Self-Awareness