RecLLM-R1: A Two-Stage Training Paradigm with Reinforcement Learning and Chain-of-Thought v1

Documenti analoghi

• Thinking on the Fly: Test-Time Reasoning Enhancement via Latent Thought Policy Optimization
  di: Ye, Wengao, et al.
  Pubblicazione: (2025)
• Latent-Space Contrastive Reinforcement Learning for Stable and Efficient LLM Reasoning
  di: Shan, Lianlei, et al.
  Pubblicazione: (2026)
• GeoLocSFT: Efficient Visual Geolocation via Supervised Fine-Tuning of Multimodal Foundation Models
  di: Yi, Qiang, et al.
  Pubblicazione: (2025)
• Thoughts-as-Planning: Latent World Models for Chain-of-Thoughts Optimization via Reinforcement Planning
  di: Liu, Dong, et al.
  Pubblicazione: (2026)
• Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs
  di: Xia, Yu, et al.
  Pubblicazione: (2024)