ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression

Documenti analoghi

• TRiMS: Real-Time Tracking of Minimal Sufficient Length for Efficient Reasoning via RL
  di: Bian, Tingcheng, et al.
  Pubblicazione: (2026)
• GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning
  di: Luo, Jinchang, et al.
  Pubblicazione: (2025)
• ThinkDrive: Chain-of-Thought Guided Progressive Reinforcement Learning Fine-Tuning for Autonomous Driving
  di: Zhao, Chang, et al.
  Pubblicazione: (2026)
• ExpLLM: Towards Chain of Thought for Facial Expression Recognition
  di: Lan, Xing, et al.
  Pubblicazione: (2024)
• Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy
  di: Li, Zeju, et al.
  Pubblicazione: (2025)