Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs

Documenti analoghi

• RISE: Reasoning Enhancement via Iterative Self-Exploration in Multi-hop Question Answering
  di: He, Bolei, et al.
  Pubblicazione: (2025)
• Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction
  di: Zhang, Yuzhe, et al.
  Pubblicazione: (2026)
• Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering
  di: He, Bolei, et al.
  Pubblicazione: (2025)
• CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning
  di: Lan, Yangsong, et al.
  Pubblicazione: (2026)
• ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning
  di: Hou, Bairu, et al.
  Pubblicazione: (2025)