Efficient LLM Reasoning: 7 Papers That Cut Token Costs by Up to 84%
Seven papers fix LLM overthinking: Sketch-of-Thought cuts tokens 84%, shorter chains boost accuracy 34.5%, and budget-aware prompting halves costs.
Seven papers fix LLM overthinking: Sketch-of-Thought cuts tokens 84%, shorter chains boost accuracy 34.5%, and budget-aware prompting halves costs.