In a metastable Markov model of reasoning, search and RL improve hitting times by boosting rare hard edges, and distilling clusters into a meta-chain preserves escape dynamics.
How far can transformers reason? T he locality barrier and inductive scratchpad
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
In a metastable Markov model of reasoning, search and RL improve hitting times by boosting rare hard edges, and distilling clusters into a meta-chain preserves escape dynamics.