LeTS: Learning to Think-and-Search via Process-and-Outcome Reward Hybridization

Documenti analoghi

• Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
  di: Yu, Zewei, et al.
  Pubblicazione: (2026)
• DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
  di: Zhang, Qi, et al.
  Pubblicazione: (2026)
• FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts
  di: Wang, Xinyi, et al.
  Pubblicazione: (2025)
• Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection
  di: Yang, Shenzhi, et al.
  Pubblicazione: (2025)
• ALPS: Attention Localization and Pruning Strategy for Efficient Alignment of Large Language Models
  di: Chen, Hao, et al.
  Pubblicazione: (2025)