Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense

Documenti analoghi

• J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning
  di: Whitehouse, Chenxi, et al.
  Pubblicazione: (2025)
• Jointly Reinforcing Diversity and Quality in Language Model Generations
  di: Li, Tianjian, et al.
  Pubblicazione: (2025)
• OptimalThinkingBench: Evaluating Over and Underthinking in LLMs
  di: Aggarwal, Pranjal, et al.
  Pubblicazione: (2025)
• Bridging Offline and Online Reinforcement Learning for LLMs
  di: Lanchantin, Jack, et al.
  Pubblicazione: (2025)
• The Majority is not always right: RL training for solution aggregation
  di: Zhao, Wenting, et al.
  Pubblicazione: (2025)