Hanyu Lai

AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework

LogicEvolve: Advancing Logical Reasoning Toward Self-Evolution

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents

WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents