RL Data ScalingBinfeng Xu
Agent Research · NVIDIA
I’m focusing on advancing RL systems for language Agents – infra, algorithms, harness and data/env, optimized as a whole.
I built Polar, the first open framework bridging LLM post-training and harness engineering. Skill2Env democratizes RL data scaling via collectively contributed Skills. My research covers agentic post-training infrastructure and algorithms, terminal/computer-use agent, vertical harness (eg. autoresearch) and continual learning.
I believe AGI is an grokking effect over shared human values and tastes, and the overall recipe should be transparent to all.
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 enjoy art, training large neural nets and petting cats.
