概念
reasoning chain-of-thought
创建2026-04-15
更新2026-04-15
阅读量级1 分钟
概念导读

Chain-of-Thought (CoT) reasoning is a prompting technique where language models generate intermediate reasoning steps before producing a final answer. CoT prompting dramatically improves performance on complex reasoning tasks and underpins modern reasoning models like those in qwen3. It is foundational to techniques like star (Self-Taught Reasoner) and plays...

  1. Related
  2. References

Chain of Thought

Chain-of-Thought (CoT) reasoning is a prompting technique where language models generate intermediate reasoning steps before producing a final answer. CoT prompting dramatically improves performance on complex reasoning tasks and underpins modern reasoning models like those in qwen3. It is foundational to techniques like star (Self-Taught Reasoner) and plays a central role in reasoning-distillation.

  • qwen3 — Qwen3 supports thinking/non-thinking mode toggling, leveraging CoT reasoning
  • star — Self-Taught Reasoner generates its own CoT traces for self-improvement
  • reasoning-distillation — Transferring CoT reasoning abilities from teacher to student models
  • thinking-budget — Compute allocation for extended CoT reasoning

References

  • Wei et al. (2022). "Chain-of-Thought Prompting Elicits Reasoning in Large Language Models." NeurIPS.