RLVR for LLMs tolerates up to 15% verifier noise with validation accuracy within 2 points of clean baselines across three model families and two task domains.
S1: Simple Test-Time Scaling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Imperfect Verifier is Good Enough: Learning with Noisy Rewards
RLVR for LLMs tolerates up to 15% verifier noise with validation accuracy within 2 points of clean baselines across three model families and two task domains.