RL Data ScalingBinfeng Xu
Agent Research · NVIDIA
I’m a researcher at Nvidia, advancing RL systems for language agents – infra, algorithms, data/env and harness, from a unified view.
I built Polar, the first open RL framework bridging agent post-training and harness engineering. To scale RL data for agents, Skill2Env turns web-crawled Agent Skills into verifiable terminal tasks. FlashREINFORCE presents an elegant RL recipe to reduce instability and false credit-assignment in long-horizon async RL.
My recent publications span terminal/computer-use agent, post-training infrastructure and algorithm, vertical harness (eg. autoresearch) and continual learning.
Research
RL Data Scaling
Async RL Recipe
Agent RL Infra
Agent RL Infra
Agent Harness
Memory Efficient RL
Agent Harness / AutoResearch
Computer-use Agent
Multimodal LLM
RL Recipe
Agent HarnessBlog
Misc
I play all games by Hidetaka Miyazaki. I played Kaggle to learn ML during school, where I ranked 1% (657th of 200,000+). I enjoy art, training large neural nets and petting cats.
