Scholar
Guangya Wan
Google Scholar ID: Um_KuoYAAAAJ
University of Virginia
Citations & Impact
Citations
119
H-index
5
i10-index
4
Publications
14
Co-authors
3
list available
Publications
Resume (English only)
Academic Achievements
- [{'PaperTitle': 'Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning', 'Conference/Journal': 'ACL Findings 2025'}, {'PaperTitle': 'COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context', 'Status': 'Under review, 2025'}, {'PaperTitle': 'BEACON: Bayesian Optimal Stopping for Efficient LLM Sampling', 'Status': 'Under review, 2025'}, {'PaperTitle': 'Reasoning-Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling', 'Conference/Journal': 'NAACL 2025'}, {'PaperTitle': 'Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English', 'Status': 'ARR (under review)'}, {'PaperTitle': 'Bridging Causal Discovery and Large Language Models: A Survey', 'Conference/Journal': 'IJCAI 2025'}, {'PaperTitle': 'ProAI: Proactive Multi-Agent Conversational AI for Psychiatric Diagnosis', 'Status': 'ARR (under review)'}, {'PaperTitle': 'Deep Learning on Intrapartum FHR to Predict Acidemia at Birth', 'Conference/Journal': 'AJOG, 2024'}, {'PaperTitle': 'Two-step LightGBM for Human West Nile Virus Risk in Chicago', 'Conference/Journal': 'PLOS ONE 19(1): e0296283, 2024'}, {'PaperTitle': 'Fair Admission Risk Prediction with Proportional Multicalibration', 'Conference/Journal': 'CHIL, 2023'}]
Background
- Research interests include LLM agents, multi-agent systems, reasoning, and efficiency. Previously, he earned an M.S. in Biostatistics at Harvard, working with William La Cava on fairness-aware ML in healthcare. Before that, he completed his B.S. in Statistics (Summa Cum Laude) at UIUC.
Miscellany
- Outside research, he enjoys exploration and the outdoors (visited 24 U.S. National Parks), photography (nature and astrophotography), and gaming (Teamfight Tactics).
