LatentRevise performs first-order optimization on reasoning prefix embeddings from failed rollouts to generate longer, self-reflective, correct trajectories that improve SFT and RLVR performance on math benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LatentRevise: Learning from Zero-Hit Reasoning
LatentRevise performs first-order optimization on reasoning prefix embeddings from failed rollouts to generate longer, self-reflective, correct trajectories that improve SFT and RLVR performance on math benchmarks.