RL Data ScalingBinfeng Xu
Agent Research · NVIDIA
I’m a researcher at Nvidia advancing RL systems for agents, coupling training infra, recipe, data/env and harness design.
My recent study covers terminal/computer-use agent, post-training infrastructure and algorithm, vertical harness (eg. autoresearch) and continual learning. For example, Polar is the first open RL framework realizing scalable any-harness rollout. To scale agentic RL data in the open, Skill2Env turns web-crawled Agent Skills into verifiable terminal tasks. FlashREINFORCE corrects false credit-assignment and train-inference mismatch to stablize long-horizon async RL.
Research
RL Data Scaling
Async RL Recipe
Agent RL Infra
Agent Harness
Memory Efficient RL
Agent Harness / AutoResearch
Computer-use Agent
Agent RL Infra
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.
