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 focuses on post-training methods for foundation models. I am particularly interested in enhancing models' agentic reasoning capabilities via efficient context processing and tool augmentation, especially for complex long-horizon tasks.

My research is partially supported by the National Science Foundation Graduate Research Fellowship and the Apple Scholars in AI/ML Ph.D. Fellowship. Before Duke, I worked with Antonios Anastasopoulos on low-resource NLP. Currently, I am a research intern at Apple Foundation Models team working on multi-modal post-training.

                




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
Batch-of-Thought: Cross-Instance Learning for Enhanced LLM Reasoning
Xuan Yang, Furong Jia, Roy Xie, Xiong Xi, Hengwei Bian, Jian Li, Monica Agrawal
ACL, 2026 (Oral)
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 (Oral)
Publication Image
Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals
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