Budget-matched evaluations and partial-prompt contamination probes show several RLVR reasoning gaps shrink or vanish once budgets, prompts, and dataset versions are controlled.
Andre He, Daniel Fried, and Sean Welleck
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards
Budget-matched evaluations and partial-prompt contamination probes show several RLVR reasoning gaps shrink or vanish once budgets, prompts, and dataset versions are controlled.