← authors · overview

• WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
  2025 · 1 citations
• Process Reward Informed Tree Rollout for Effective Multi-Turn RL
  2026
• Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control
  2026
• Rethinking Importance Sampling in LLM Policy Optimization: A Cumulative Token Perspective
  2026
• Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training
  2026
• HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
  2026
• Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
  2025
• Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse
  2025
• Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
  2025
• Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
  2025
• WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
  2025