A training pipeline called T1 scales RL for LLM reasoning via diverse sampling and rewards, and claims that longer allowed generations directly improve math accuracy without verifiers.
Back to basics: Revisiting reinforce style optimization for learning from human feedback in llms
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
-
T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling
A training pipeline called T1 scales RL for LLM reasoning via diverse sampling and rewards, and claims that longer allowed generations directly improve math accuracy without verifiers.