FEST improves RLVR sample efficiency on math and coding benchmarks by combining supervised signals, on-policy signals, and decaying weights on just 128 randomly chosen demonstrations, matching full-dataset baselines.
Scheduled sampling for sequence prediction with recurrent neural networks
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
-
Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance
FEST improves RLVR sample efficiency on math and coding benchmarks by combining supervised signals, on-policy signals, and decaying weights on just 128 randomly chosen demonstrations, matching full-dataset baselines.