Across four frontier reasoning models, 61–93% of correct chain-of-thought steps are redundant, and this over-thinking is provably optimal under any length-agnostic outcome reward.
k⋆ = 1 segmented step
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
How Much Thinking is Enough? Quantifying and Understanding Redundancy in LLM Reasoning
Across four frontier reasoning models, 61–93% of correct chain-of-thought steps are redundant, and this over-thinking is provably optimal under any length-agnostic outcome reward.