Exact RMT-derived formula for CoT generalization error in linear ICL reveals phase transition between exponential/polynomial improvement, saturation, and overthinking regimes depending on depth, pretraining, and context length.
Theoretical perspectives on data quality and synergistic effects in pre- and post-training reasoning models, 2026
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Asymptotic Theory of Chain-of-Thought in In-Context Learning
Exact RMT-derived formula for CoT generalization error in linear ICL reveals phase transition between exponential/polynomial improvement, saturation, and overthinking regimes depending on depth, pretraining, and context length.