An adaptive, difficulty-aware length reward for RL training makes large reasoning models produce shorter chains of thought while matching or improving math accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learn to Reason Efficiently with Adaptive Length-based Reward Shaping
An adaptive, difficulty-aware length reward for RL training makes large reasoning models produce shorter chains of thought while matching or improving math accuracy.