Writing-RL applies adaptive curriculum RL with pairwise rewards and dynamic scheduling to enhance long-form writing in 7B LLMs over SFT baselines and shows generalization to long-input reasoning tasks.
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
UNVERDICTED 1representative citing papers
citing papers explorer
-
Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement Learning
Writing-RL applies adaptive curriculum RL with pairwise rewards and dynamic scheduling to enhance long-form writing in 7B LLMs over SFT baselines and shows generalization to long-input reasoning tasks.