Papers

• BeamPERL: Parameter-Efficient RL with Verifiable Rewards Specializes Compact LLMs for Structured Beam Mechanics Reasoning (2026)
  Tarjei Paule Hage et al.
  1.94
• Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning (2026)
  NVIDIA et al.
  1.94
• The Invisible Leash: Why RLVR May Not Escape Its Origin (2025)
  Fang Wu et al.
  1.28
• Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models (2025)
  Zhipeng Chen et al.
  1.28
• Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training (2025)
  Chenlu Ye et al.
  1.28
• VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models (2025)
  Guochao Jiang et al.
  1.28
• ExGRPO: Learning to Reason from Experience (2025)
  Runzhe Zhan et al.
  1.28
• ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models (2025)
  Yuqi Liu et al.
  1.28
• EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning (2025)
  He Du et al.
  1.28
• Search Self-play: Pushing the Frontier of Agent Capability without Supervision (2025)
  Hongliang Lu et al.
  1.28
• Document Understanding, Measurement, and Manipulation Using Category Theory (2025)
  Jared Claypoole et al.
  1.28
• SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning (2025)
  Salman Rahman et al.
  1.28