Boosting LLM Reasoning via Human-Inspired Reward Shaping

Documenti analoghi

• From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
  di: Jiang, Xitai, et al.
  Pubblicazione: (2026)
• Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
  di: Lu, Rui, et al.
  Pubblicazione: (2025)
• What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning
  di: Ma, Yiran, et al.
  Pubblicazione: (2024)
• DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
  di: Li, Gang, et al.
  Pubblicazione: (2025)
• DGRO: Enhancing LLM Reasoning via Exploration-Exploitation Control and Reward Variance Management
  di: Su, Xuerui, et al.
  Pubblicazione: (2025)