一作ICLR 2026Poster· Applications / Language, Speech and Dialog
Solving the Granularity Mismatch: Hierarchical Preference Learning for Long-Horizon LLM Agents
Heyang Gao · Zexu Sun · Erxue Min · Hengyi Cai · Shuaiqiang Wang · Dawei Yin · Xu Chen
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。
Heyang Gao · Zexu Sun · Erxue Min · Hengyi Cai · Shuaiqiang Wang · Dawei Yin · Xu Chen
Zexu Sun · Yongcheng Zeng · Erxue Min · Heyang Gao · Bokai Ji · Dugang Liu · Xing Tang · xiuqiang He · Xu Chen
Contemporary progress in Large Language Models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable rewards. However, “zero-RL” approaches relying on fixed prompt templates introduce substantial sampling inefficiencies for weak LLMs, as most prob...