A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
Thinkswitcher: When to think hard, when to think fast
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
ACCEPT 1representative citing papers
citing papers explorer
-
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.