The paper claims PRM generalization error controls test-time compute efficiency and that the proposed CATS controller improves accuracy on MATH-500 and AIME24.
Learning to reason with llms
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Reward Model Generalization for Compute-Aware Test-Time Reasoning
The paper claims PRM generalization error controls test-time compute efficiency and that the proposed CATS controller improves accuracy on MATH-500 and AIME24.