作者位次 #6/7ICLR 2026Poster· Reinforcement Learning / Deep RL
Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
Xichen Zhang · Sitong Wu · Yinghao Zhu · Haoru Tan · Shaozuo Yu · Ziyi He · Jiaya Jia
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。
Xichen Zhang · Sitong Wu · Yinghao Zhu · Haoru Tan · Shaozuo Yu · Ziyi He · Jiaya Jia
Xichen Zhang · Ziyi He · Yinghao Zhu · Sitong Wu · Shaozuo Yu · Meng Chu · Wenhu Zhang · Haoru Tan · Jiaya Jia
Search agents have emerged as a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. However, training these agents via Reinforcement Learning (RL) faces a critical dilemma: interacting with live commercial Web APIs is prohibitively expensive, while relying on static data...