LCPO trains L1 reasoning models to adhere to prompt-specified CoT lengths, supporting accuracy-compute trade-offs and yielding short reasoning models that outperform larger baselines at matched lengths.
Thus, the maximum real part is approximately 625.6
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
LCPO trains L1 reasoning models to adhere to prompt-specified CoT lengths, supporting accuracy-compute trade-offs and yielding short reasoning models that outperform larger baselines at matched lengths.