一作ICLR 2026Poster
Buffer Matters: Unleashing the Power of Off-Policy Reinforcement Learning in Large Language Model Reasoning
Xu Wan · Yansheng Wang · Wenqi Huang · Mingyang Sun
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。
Xu Wan · Yansheng Wang · Wenqi Huang · Mingyang Sun
Wenyue Xu · Xu Wan · Wei Wang · Wenqi Huang · Wotao Yin · Shengjie Zhao · Mingyang Sun
The slow thinking paradigm has been widely validated to enhance the reasoning capabilities of Large Language Models (LLMs), but it introduces notable reasoning inefficiencies: models often overthink simple tasks while prematurely shifting their reasoning paths when addressing complex problems. To...