作者位次 #3/5ICLR 2026Oral
LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
Yuhao Wu · Yushi Bai · Zhiqiang Hu · Roy Ka-Wei Lee · Juanzi Li
强化学习与后训练OpenReview
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Yuhao Wu · Yushi Bai · Zhiqiang Hu · Roy Ka-Wei Lee · Juanzi Li
Yuhao Wu · Yushi Bai · Zhiqiang Hu · Juanzi Li · Roy Ka-Wei Lee
Long-form text generation remains a significant challenge for large language models (LLMs), particularly in maintaining coherence, ensuring logical consistency, and preserving text quality as sequence length increases. To address these limitations, we propose \textit{SuperWriter} -Agent, an agent...