Haolin Chen

Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning

ToolLibGen: Scalable Automatic Tool Creation and Aggregation for LLM Reasoning

LoCoBench: A Benchmark for Long-Context Large Language Models in Complex Software Engineering

Language Models are Hidden Reasoners: Unlocking Latent Reasoning Capabilities via Self-Rewarding