Shusheng Xu

Unlocking Long-Horizon Agentic Search with Large-Scale End-to-End RL

AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Reasoning Is Not a Race: When Stopping Early Beats Going Deeper

How Far Are We from Optimal Reasoning Efficiency?

On Designing Effective RL Reward at Training Time for LLM Reasoning