Roy Xie Small Image

Duke University

I am a third-year Computer Science Ph.D. student at Duke NLP, advised by Bhuwan Dhingra. My research mainly focuses on post-training methods for LLMs. I am particularly interested in developing efficient algorithms to improve LLMs reasoning ability, especially for complex multi-step agentic tasks.

My research is partially supported by the Apple Scholars in AI/ML Ph.D. Fellowship and the National Science Foundation Graduate Research Fellowship. Before Duke, I worked with Antonios Anastasopoulos on low-resource NLP.

                




profile photo

Recent Publications

Publication Image
Interleaved Reasoning for Large Language Models via Reinforcement Learning
Roy Xie, David Qiu, Deepak Gopinath, Dong Lin, Yanchao Sun, Chong Wang, Saloni Potdar, Bhuwan Dhingra
Preprint
Publication Image
When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training
Sanxing Chen, Xiaoyin Chen, Yukun Huang, Roy Xie, Bhuwan Dhingra
ICLR, 2026
Publication Image
Over-Searching in Search-Augmented Large Language Models
Roy Xie, Deepak Gopinath, David Qiu, Dong Lin, Haitian Sun, Saloni Potdar, Bhuwan Dhingra
EACL, 2026
Publication Image
Language Models are Symbolic Learners in Arithmetic
Chunyuan Deng, Zhiqi Li, Roy Xie, Ruidi Chang, Hanjie Chen
TMLR, 2026
Publication Image
Language Models (Mostly) Know When to Stop Reading
Roy Xie, Junlin Wang, Paul Rosu, Chunyuan Deng, Bolun Sun, Zihao Lin, Bhuwan Dhingra
NeurIPS, 2025
Publication Image
Improving Model Alignment Through Collective Intelligence of Open-Source Models
Junlin Wang, Roy Xie, Shang Zhu, Jue Wang, Ben Athiwaratkun, Bhuwan Dhingra, Shuaiwen Leon Song, Ce Zhang, James Zou
ICML, 2025