Xin Cong

Test-Time Exploration in Unknown Environments

Diversity-aware Training for Test-time Scaling

Reflective Reinforcement Tool Learning

Generalizing Experience for Language Agents with Hierarchical MetaFlows

WorkflowLLM: Enhancing Workflow Orchestration Capability of Large Language Models

Rational Decision-Making Agent with Learning Internal Utility Judgment

AC-Reason: Towards Theory-Guided Actual Causality Reasoning with Large Language Models

Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

Learning Evolving Tools for Large Language Models