Guangya (Wayne) Wan — Ph.D. Candidate, University of Virginia

Overview

I’m a Ph.D. candidate in Data Science at the University of Virginia, advised by Sheng Li (RISE Lab). My research interests are LLM agents, multi‑agent systems, reasoning, and efficiency.

Previously, I earned an M.S. in Biostatistics at Harvard, working with William La Cava on fairness-aware ML in healthcare. Before that, I completed my B.S. in Statistics (Summa Cum Laude) at UIUC.

Research interests

LLM Agents Multi‑Agent Systems Reasoning Efficiency

Availability: Seeking a Summer 2026 research internship in LLM agents, multi‑agent systems, reasoning, and efficiency.

Recent news Our paper “Derailer‑Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning” (LLM reasoning & reliability) has been accepted to ACL Findings 2025.

COMPASS preprint available: arXiv.
BEACON preprint available: PDF.

Education

University of Virginia — Ph.D. in Data Science

08/2023 – 05/2027 (expected) · Advisor: Sheng Li

Focus: LLM reasoning & agents; fairness & uncertainty; social intelligence

Harvard University — M.S. in Biostatistics (Data Science)

08/2021 – 05/2023 · GPA: 3.89

UIUC — B.S. in Statistics (Summa Cum Laude)

09/2017 – 12/2020 · Minor: CS & Mathematics · GPA: 3.94

Selected Publications

COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context. Under review, 2025. Paper

G. Wan, M. Ling, X. Ren, R. Han, S. Li, Z. Zhang
BEACON: Bayesian Optimal Stopping for Efficient LLM Sampling. Under review, 2025. Paper

G. Wan, Z.S. Xu, S. Zorc, M. Baucells, M. Hu, H. Wang, S. Li
Reasoning-Aware Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling. NAACL 2025. Paper

G. Wan, Y. Wu, J. Chen, S. Li
Derailer-Rerailer: Adaptive Verification for Efficient and Reliable Language Model Reasoning. ACL Findings 2025. Paper

G. Wan, Y. Wu, H. Wang, S. Zhao, J. Chen, S. Li
Disparities in LLM Reasoning Accuracy and Explanations: A Case Study on African American English. ARR (under review). Paper

R. Zhou*, G. Wan*, S. Gabriel, S. Li, A. Gates, M. Sap, T. Hartvigsen (*equal)
Bridging Causal Discovery and Large Language Models: A Survey. IJCAI 2025. Paper

G. Wan, Y. Lu, Y. Wu, M. Hu, S. Li
ProAI: Proactive Multi-Agent Conversational AI for Psychiatric Diagnosis. ARR (under review). Paper

Y. Wu*, G. Wan*, J. Li, S. Zhao, L. Ma, T. Ye, I. Pop, Y. Zhang, J. Chen
Deep Learning on Intrapartum FHR to Predict Acidemia at Birth. AJOG, 2024. Paper

J.A. McCoy, L.D. Levine, G. Wan, et al.
Two-step LightGBM for Human West Nile Virus Risk in Chicago. PLOS ONE 19(1): e0296283, 2024. Paper

G. Wan, J. Allen, W. Ge, et al.
Fair Admission Risk Prediction with Proportional Multicalibration. CHIL, 2023. Paper

W.G. La Cava, E. Lett, G. Wan

Full list on Google Scholar.

Experience

Student Researcher — Google

Mountain View, CA · 05/2025–Present

Data Scientist Intern — Chewy

Boston, MA · 06/2022–08/2022

ML Research Intern — Boston Children’s Hospital (CHIP)

Boston, MA · 01/2022–04/2023

ML Research Intern — NCSA (Student Pushing Innovation)

Champaign, IL · 06/2019–12/2020

About Myself

Outside research, I enjoy exploration and the outdoors (visited 24 U.S. National Parks), photography (nature and astrophotography), and gaming (Teamfight Tactics).