I am a third-year PhD student studying computer science at UC Santa Cruz, advised by Chenguang Wang. Previously, I completed my Bachelor’s degree in Computer Science and Mathematics, as well as a Master’s degree in Computer Science, both at Washington University in St. Louis. You can find my CV here.
My research interests include agentic AI, post-training, and LLM safety. I am currently a student researcher at ByteDance Seed, working on RL infrastructure. Before that, I was a visiting researcher at Scale AI. I am also a project lead for rLLM. When not engaging in research, I’m frequently rock climbing 🧗.
selected publications
See the full list of publications. (*) denotes equal contribution.
-
ObsSpec: Accelerating Agentic Reinforcement Learning with Observation Speculation
Kyle Montgomery, Wang Zhang, and Chenguang Wang
Oct 2026
-
Budget-aware Test-time Scaling via Discriminative Verification
Kyle Montgomery*, Sijun Tan*, Yuqi Chen, Siyuan Zhuang, Tianjun Zhang, Raluca Ada Popa, and Chenguang Wang
In Workshop on Efficient Reasoning at NeurIPS 2025, Oct 2025
-
rLLM: A Framework for Post-Training Language Agents
Sijun Tan, Michael Luo, Colin Cai, Tarun Venkat, Kyle Montgomery, Aaron Hao, Tianhao Wu, Arnav Balyan, and 5 more authors
Jul 2025
-
JudgeBench: A Benchmark for Evaluating LLM-Based Judges
Sijun Tan*, Siyuan Zhuang*, Kyle Montgomery*, Willian Y. Tang, Alejandro Cuadron, Chenguang Wang, Raluca Ada Popa, and Ion Stoica
In Proceedings of the Thirteenth International Conference on Learning Representations, Apr 2025
-
Agent Instructs Large Language Models to be General Zero-Shot Reasoners
Nicholas Crispino, Kyle Montgomery, Fankun Zeng, Dawn Song, and Chenguang Wang
In Proceedings of the Forty-first International Conference on Machine Learning, Jul 2024
