Fangzhi Xu

ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows

Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning

MUR: Momentum Uncertainty guided Reasoning for Large Language Models

OS-ATLAS: Foundation Action Model for Generalist GUI Agents

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding

AgentStore: Scalable Integration of Heterogeneous Agents As Specialized Generalist Computer Assistant