Scholar
Kyle Montgomery
Google Scholar ID: O8tnCagAAAAJ
UC Santa Cruz
Citations & Impact
Citations
304
H-index
3
i10-index
3
Publications
9
Co-authors
4
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including:
- - rLLM v0.2: RL Training over General Agentic Programs
- - Weak Discriminative Verification Enables Strong Test-time Scaling
- - LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
- - VMDT: Decoding the Trustworthiness of Video Foundation Models
- - rLLM: A Framework for Post-Training Language Agents
- - JudgeBench: A Benchmark for Evaluating LLM-Based Judges
- - Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning
- - Agent Instructs Large Language Models to be General Zero-Shot Reasoners
Research Experience
- Project lead for rLLM; involved in multiple research projects such as LLM post-training, agentic AI, etc.
Education
- Currently a second-year PhD student in Computer Science at UC Santa Cruz, advised by Chenguang Wang. Previously, completed 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.
Background
- Research interests include LLM post-training, agentic AI, and scaling test-time compute for hard-to-verify tasks. Also a project lead for rLLM.
Miscellany
- Frequently rock climbs in free time
