Mitigating Overthinking in Large Reasoning Models via Difficulty-aware Reinforcement Learning

Documenti analoghi

• Mitigating Overthinking in Large Reasoning Models via Manifold Steering
  di: Huang, Yao, et al.
  Pubblicazione: (2025)
• Beyond Error-Based Optimization: Experience-Driven Symbolic Regression with Goal-Conditioned Reinforcement Learning
  di: Sun, Jianwen, et al.
  Pubblicazione: (2026)
• Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation
  di: Bin, Yi, et al.
  Pubblicazione: (2025)
• DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models
  di: Shen, Yi, et al.
  Pubblicazione: (2025)
• Think How to Think: Mitigating Overthinking with Autonomous Difficulty Cognition in Large Reasoning Models
  di: Liu, Yongjiang, et al.
  Pubblicazione: (2025)